사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/cryskai/crysk --skill crysk-ci-setup시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Activation Contract
Load when the user asks to:
- Add Crysk to GitHub Actions CI, scaffold
.github/workflows/crysk.yml, or configure secrets. No local install is needed: the workflow file is the whole install. - Configure the models per role in CI, or OpenCode (
CRYSK_MODELS,CRYSK_OPENCODE_*secrets, DeepSeek, mixed Claude+OpenCode, fallbacks). - Move a workflow off the removed inputs (
CRYSK-INPUT-REMOVED:claude-token,anthropic-api-key,opencode-authwith theOPENCODE_AUTH_JSONsecret,routingwith theCRYSK_ROUTINGvariable). - Tune CI spend / re-review / admission policy.
- Retrigger a skipped CI review (size, admission, or budget) without running the review locally.
- Reduce review noise: fewer comments (
post_min_severity) or fewer blocking findings that are real but improbable (materiality_gate).
Hard Rules
- Zero secret leakage: NEVER print,
cat, commit, or log API keys, tokens, or an OpenCodeauth.jsonrecord. Reference${{ secrets.* }}names only. Inspectauth.jsonkeys and `type` only. - One `CRYSK_
secret per credential, nothing else:**CRYSKCLAUDEOAUTHTOKEN` (subscription), `CRYSKCLAUDEAPIKEY,CRYSKOPENCODE<P>APIKEYper OpenCode provider,CRYSKOPENCODEOPENAIOAUTH` for an OpenAI subscription. The workflow names each one in its `crysk-secrets` block, never `toJSON(secrets)`. The old `CLAUDECODEOAUTHTOKEN,ANTHROPICAPIKEYandOPENCODEAUTHJSONsecrets and theCRYSKROUTING` variable are read by nothing. Models per role go in the public variable `CRYSKMODELS(no credentials in it), the Claude order inCRYSKCREDENTIALS`, the OpenCode providers in `CRYSKOPENCODE_PROVIDERS`. - No install needed: run every Crysk command as
npx -y crysk <command>(Node is enough; the package brings its own Bun). A globalcryskon PATH is the same command. CI itself needs no local CLI at all: the workflow runs the action.npx -y crysk skills installinstalls the Crysk, triage, and CI-setup skills into every detected coding agent, with no TTY and no MCP or launchd registration (neither is needed for the CI loop, and npx's temporary cache refuses them). - Deterministic scaffolding: Run
npx -y crysk setup --ci(ornpx -y crysk ci init) with the interview's flags. It writes the one workflow file,.github/workflows/crysk.yml(a repo that already haspr-hero.ymlkeeps it:--forcerewrites it in place, and setup refuses to add a second file beside it). Do not fabricate it from memory. Fallback: copyassets/workflow.yml. Never scaffold apr-hero-force.yml; it is retired. - `fetch-depth: 0` is mandatory on
actions/checkout@v4. - Gate mode: the
cryskcommit status is the required check (the legacypr-herostatus is no longer posted). The scaffold writesmode: gateexplicitly: blocking findings, a size or spend-ceiling skip, and a crash set it red. Every review rule that skips a push (low-risk delta, once per PR,/crysk stop, the attempt budget used up,manual_only) carries the last verdict; answered blocking findings turn a carried red green, marked unverified. Under the attempt budget used up ormanual_only, that green is heldpendinginstead, so a push past the budget or undermanual_onlynever turns green without a/crysk reviewor a/crysk override.mode: advisorykeeps it green for a finished review. The job's exit code stays0on findings either way, so do not gate on the job. - Required permissions:
contents: read,pull-requests: write,issues: write,statuses: write, `checks: write`, `actions: read` (the admission gate lists past runs; a private repo 403s without it). Template inassets/workflow.ymlincludes all six. - Retrigger is a PR comment: `gh pr comment <n> --body "/crysk review"`. GitHub Actions runs the review on the runner with
--force. The comment must be exactly/crysk review(or/crysk review --full;/pr-hero reviewon a workflow scaffolded before the rename, see the/cryskvs/pr-herobullet), and its author needs write access; the action refuses anyone else. Do not runcrysk review --forcelocally when the review should happen in CI.gh run rerunon a skipped run re-evaluates the gates and does not force. In this repo a comment run checks out the PR head commit beforeuses: ./, so it runs the PR's own engine, not the default branch's. - `/crysk recheck` re-reviews the head and asks the CI adjudicator to rule on pending dismissals. It is
/crysk reviewplus--adjudicate, with the same permission check and reaction; refused on fork pull requests. Seedocs/github-actions.md("Rechecking a dismissal"). - `/crysk stop` stops automatic reviews on the PR. Post it before a push that should not be reviewed: CI admission skips every later automatic review, carrying the last verdict, until a
/crysk reviewor/crysk recheckcomment. It counts only from a user with write access (checked at admission), starts no run, and never turns the gate green. Seedocs/github-actions.md("Stopping automatic reviews"). - `--force` never widens discovery; `--full` does. When a prior review of the same head was hollow or wrong and re-runs report "No changes to discover", comment
/crysk review --full. It passes--full, which re-discovers the whole PR range. - When the comment trigger takes effect: GitHub reads a comment-triggered workflow from the default branch (for this repo,
main, notdev), so/crysk reviewworks only once the workflow file (crysk.yml, orpr-hero.ymlin a repo set up before the rename) with itsissue_commenttrigger is merged there; a user repo also needs an action release that handles the comment, through the@v0it pins. - `/crysk` vs `/pr-hero`: the commands are
/crysk review,/crysk recheck,/crysk overrideand/crysk stop; the action still accepts/pr-hero …for one version. Apr-hero.ymlscaffolded before the rename filters only/pr-hero …, so a/crysk …comment starts nothing there: re-runnpx -y crysk ci init --forceto accept both, which also moves the workflow to theCRYSK_*secrets. - Legacy scaffolds: a
pr-hero.ymlscaffolded before the comment trigger has noissue_commentlistener, so a comment does nothing. There, usegh workflow run pr-hero-force.yml -f pr=<n>(add-f full=trueto re-discover), or re-scaffold withnpx -y crysk ci init --force, which leavespr-hero-force.ymlin place. - Minimum action version: this workflow listens to comments, and only an action release that ships the comment handling checks the command and the commenter's write access. An older action reviews on ANY comment starting with
/crysk review, from anyone who can comment. Never pair this workflow with an older action; a pinned tag or sha must be at or after that release. - Older heads (this repo): a comment run loads the PR head's own
action.yml, so on a head from before the comment handling it reviews without reading the comment (no force, no--full); merge or rebase the PR onto a base that has it first. - Trust (this repo): a comment run runs the PR head's code, including its
bun install, with the workflow's secrets, so write access is checked twice: by the workflow's pre-checkout step (fail closed, before any head code runs) and again by the head'saction.yml. - Admission config is repo-level: Write
.crysk/config.jsonon the default branch. That file rejectsmodelsandcredentials: they are person-layer only ($HOME/.crysk/config.jsonon the runner, written fromvars.CRYSK_MODELSandvars.CRYSK_CREDENTIALS). - `.cryskignore` is read from the base ref, not the PR branch, in CI.
- Models and OpenCode are DATA: the scaffold passes
models: ${{ vars.CRYSK_MODELS }},credentials: ${{ vars.CRYSK_CREDENTIALS }}and five OpenCode slot lines driven byvars.CRYSK_OPENCODE_PROVIDERS. UnsetCRYSK_MODELS= Claude CI. Never a per-provider Action input. A repository connected to the Crysk platform takes its models from the platform, which wins over the inputs. - OpenCode procedure: when OpenCode or mixed backends are in scope, follow
references/opencode-ci.mdbefore setting GitHub DATA (roles, model names, one secret per provider, the providers variable).
Decision Gates
| Condition | Action |
|---|---|
gh auth status succeeds | Offer gh secret set / gh variable set |
gh missing/unauthenticated | Link to repo Settings → Secrets and variables → Actions (Variables tab for CRYSK_MODELS, CRYSK_CREDENTIALS, CRYSK_OPENCODE_PROVIDERS) |
| Credential: Claude | `CRYSK_CLAUDE_OAUTH_TOKEN` — subscription (claude setup-token only, NOT keychain). `CRYSK_CLAUDE_API_KEY` — pay-as-you-go. Both set: the subscription runs unless CRYSK_CREDENTIALS is {"claude": ["api_key", "subscription"]}. |
| Credential: OpenCode | Read references/opencode-ci.md. One CRYSK_OPENCODE_<P>_API_KEY per provider + CRYSK_MODELS + CRYSK_OPENCODE_PROVIDERS. Any CRYSK_* credential counts; with none, the run fails red with the gh secret set commands. |
| openai in CI | CRYSK_OPENCODE_OPENAI_API_KEY runs metered; CRYSK_OPENCODE_OPENAI_OAUTH (base64 of the openai record of OpenCode's auth.json) is the ChatGPT subscription and wins when both are set. _OAUTH works for openai only. |
Workflow red with CRYSK-INPUT-REMOVED | It still passes claude-token, anthropic-api-key, opencode-auth or routing. npx -y crysk ci init --force, then set the CRYSK_* secrets and variables it prints. |
| Different models per step | CRYSK_MODELS maps roles to lists: default, hunter.<key>, refuter, consolidate, scout, summary, judge. Any role left on a claude: model needs a Claude secret; OpenCode-only = every role on OpenCode, e.g. {"default": ["opencode:deepseek/deepseek-v4-flash"]} (references/opencode-ci.md). |
| Several OpenCode providers in one run | Supported: up to 5 providers through the workflow's slots, each model on its own provider's secret, as primary or fallback. |
| OpenCode CLI pin | Action installs 1.18.30 iff the setup step wrote an OpenCode auth file OR the models in effect name opencode:. Never latest. |
| Fork PRs | Their pushes skip (no secrets). A user with write access comments /crysk review, and that run (base context, with secrets) reviews the fork head. Review if never reads secrets; the action checks for a CRYSK_* credential in crysk-secrets (or a login file already on the runner). |
| Spend gates | Defaults: budget-usd: 10.00 on metered routes (the run chose CRYSK_CLAUDE_API_KEY, or an OpenCode auth file was built), max-changed-lines: 4000 and max-changed-files: 50 on metered routes only; a Claude subscription route has no size limit unless the workflow or .crysk/config.json sets one. A subscription run stays unlimited unless an OpenCode auth file is also present. |
| Existing workflow | setup --ci skips; ask before --force |
| First-time admission | Recommend ci_admission_observe_only: true — references/ci-admission.md |
| User wants max CI spend | Lower ci_max_attempts and/or raise ci_rereview_min_score |
| Custom bot posts findings | Add login to ci_trusted_actors |
| Too many advisory comments on PRs | Raise the posting floor: post_min_severity: "blocking" in .crysk/config.json posts only blocking findings ("warning", the recommended floor setup writes, hides advisory suggestions only). Blocking findings always post; the gate is unchanged. |
| Blocking findings that are real but improbable keep PRs red ("an edge case that never happens") | Offer materiality_gate: true in .crysk/config.json (opt-in, off by default). An isolated judge checks each blocking finding against Crysk's posting policy; one judged not material under normal use posts as advisory and does not block. Security, credential and data-loss findings are never demoted, and any judge failure keeps the finding blocking. Cost: one sonnet call per blocking finding (about 1 per PR, roughly +$0.015 notional and +10 s per review). Pair it with post_min_severity: "blocking" to hide the demoted ones entirely. |
materiality_gate is on but nothing is ever demoted | Read the materiality record in the run's pipeline.json (in the crysk-run-* artifact). unsupported_route: the judge runs only on claude:sonnet-latest or claude:opus-latest, so a models.judge in CRYSK_MODELS that lists neither stands it down; remove that role or list one of the two. ceiling: the pipeline ceiling left no room for one judge wave (about 9 minutes). ran with judged: 0: the run had no blocking finding the safety guard leaves unprotected, so there was nothing to judge. skipped on a re-review with no new commits to review is expected (the judge is left out when nothing new is hunted). skipped anywhere else means the key did not reach the run: the repo config must be on the PR's base branch (CI reads it from there) and a global config must not set it false (the key is capped). |
| CI skipped (size, admission, or budget) | gh pr comment <n> --body "/crysk review". The review runs on GitHub Actions. Do not run crysk review --force locally for this. Legacy scaffold (no issue_comment trigger): gh workflow run pr-hero-force.yml -f pr=<n>. |
| Gate is red with blocking findings the team accepts | gh pr comment <n> --body "/crysk override" (write access, same-repo PRs only, valid for that head only; a same-head /crysk review keeps it red). |
| Prior review of the same head was hollow or wrong; re-runs say "No changes to discover" | gh pr comment <n> --body "/crysk review --full". A plain /crysk review keeps the narrowed discovery. |
Gate red: crysk: review partial (N of M hunters failed, set abc123) — /pr-hero review retries it | Some hunters failed and nothing blocking was found. gh pr comment <n> --body "/crysk review". If the same hunters fail every run, fix their route (model, credential) or override. |
Gate red: crysk: review partial again (N of M hunters failed, set abc123) — fix the failing route or /pr-hero override | The previous review of this head was partial with the same hunters failing, so a retry already failed the same way. Fix the failing hunter's route (model, credential), or gh pr comment <n> --body "/crysk override". crysk status answers override-or-fix. |
Gate error: CRYSK-CANCELLED: not reviewed — /pr-hero review reviews this head | The review run was cancelled (a newer push, or by hand). Comment /crysk review to review the head. |
CRYSK-MODEL-UNAVAILABLE (lead "Provider <name>:") | Every hunter's route names a model the provider does not serve. Fix the model id in CRYSK_MODELS (check opencode models <provider>). |
CRYSK-CRED-UNUSABLE ("The route <provider>/<model> has no usable credential record") | No CRYSK_OPENCODE_<P>_API_KEY reached the run for that provider: set it, add its token to CRYSK_OPENCODE_PROVIDERS, or move that model elsewhere in CRYSK_MODELS. |
CRYSK-CONFIG-INVALID naming the models or credentials input | CRYSK_MODELS or CRYSK_CREDENTIALS is not valid JSON or breaks a rule (the step's log names the entry). Check the same object locally under models / credentials in ~/.crysk/config.json with npx -y crysk config, then set the variable again. |
Blocking findings answered dismissed, gate still red | gh pr comment <n> --body "/crysk recheck": the CI adjudicator rules on each dismissal (at most 5 per run). On upheld, comment /crysk review: that next review stops counting it. deferred / misclassified never clear the gate. |
Gate error: CRYSK-GOTCHAS-MISSING ("the review instructions file (REVIEW.md or .crysk/gotchas.md) is empty or still the scaffold") | Write real facts into that file and delete the human-attention-required marker line (or delete the file to review with the default guidance), commit it to the default branch, then comment /crysk review. |
Gate error: CRYSK-HUNTERS-FAILED (every hunter failed) | Check the route and credential first (the CRYSK-CRED-UNUSABLE and CRYSK-MODEL-UNAVAILABLE rows). Free OpenCode models fail intermittently: comment /crysk review to retry. |
A /crysk review comment did nothing | The workflow is not on the default branch yet, the comment is not exact, the author lacks write access, or the workflow predates the comment trigger (re-scaffold with --force). |
Review Settings Interview (ask the human, never choose for them)
Before step 4, ask the human these questions in their language. Use the native question UI when available (one grouped interaction is fine). Do not pick an answer for them, and do not skip a question because a default exists: the point is that they know these settings exist.
- Re-review level (how Crysk reviews new pushes on an open PR):
- Minimal: one automatic review per PR; later pushes only on a
/crysk reviewcomment. - Balanced (recommended): re-review when the push touches risky files or the previous pass found enough (score >= 4); at most 2 automatic passes.
- Thorough: review every push, up to 4 automatic passes. Most coverage, most cost.
- Manual: nothing automatic after the first review; every re-review starts with
/crysk review.
- Gate or advisory: gate turns the
cryskcheck red on blocking findings (require it in branch protection to block merges); advisory keeps it green. - How CI pays:
- Claude subscription (
CRYSK_CLAUDE_OAUTH_TOKEN): do not ask for a budget. Tell them nobudget-usdis written: a subscription review spends quota, not dollars, and CI applies no ceiling while the run uses the subscription and noCRYSK_OPENCODE_*secret builds an OpenCode auth file (an OpenCode model brings back the $10 ceiling, so a subscription mixed with OpenCode is the API-key answer). An API key kept beside it is not used unlessCRYSK_CREDENTIALSputsapi_keyfirst. - API key (
CRYSK_CLAUDE_API_KEYor an OpenCode provider): ask for the spend ceiling per review in USD (default 10,0= none).
- Changed-lines threshold: a PR with more changed lines is skipped, not reviewed. Ask on any billing (default 4000,
0= no limit, only if they say so): unlike the budget it matters on a subscription too, where an unset threshold means no limit at all. - Advanced settings: name them, then ask whether to review them now. Each keeps a working default if skipped:
- score weights: blocking 2, advisory 1 (integers >= 1;
ci_blocking_weight,ci_advisory_weight), and the score floor 4 (ci_rereview_min_score); used only by the risk-aware and thresholded policies; - observe only (
ci_admission_observe_only): log what the rules would skip, but review every push; good for one PR cycle; - trusted actors (
ci_trusted_actors): extra GitHub logins whose Crysk markers count; - changed-files limit (
max_changed_files): a PR touching more files is skipped; unset = none on a subscription, 50 on an API key; - exclusions: patterns in
.cryskignore(gitignore syntax) the review never reads; - posting floor (
post_min_severity):suggestionposts everything,warning(recommended, and what setup writes when the key is absent) hides advisory suggestions,blockingposts only blocking findings. Hidden findings are counted in the summary comment, and the gate is unchanged; - materiality gate (
materiality_gate, off unless they say yes): blocking findings that are real but not material under normal use are posted as advisory instead of blocking, judged by an isolated sonnet call per blocking finding against Crysk's posting policy; security, credential and data-loss findings are never demoted. Tell them the cost (about one call per PR, +$0.015 notional, +10 s), that it runs on Claude only (claude:sonnet-latest, orclaude:opus-latestthroughmodels.judge), so it needs a Claude secret, and the known limit: on a re-review, a finding that already blocked on an earlier push still counts toward the gate.
On a re-run (.crysk/config.json already has re-review keys, or the workflow already exists), first show the human the current values (npx -y crysk config) and offer Keep current settings for the level and for the line threshold. When they keep them, omit --level / --max-changed-lines: passing a flag overwrites that group, including a tuned max_verification_steps.
Then pass the answers to the scaffold as flags, never as hand-written YAML:
npx -y crysk setup --ci --level <minimal|balanced|thorough|manual> --ci-mode <gate|advisory> --billing <subscription|api> --max-changed-lines <n> [--budget-usd <n>]It writes the workflow, merges the level's keys into .crysk/config.json (keeping other keys), and prints a summary of every setting. Never run it without these flags: with none it applies balanced and gate, and its summary says nobody chose them. Write any advanced answers into .crysk/config.json (and .cryskignore) afterwards. The summary setup --ci printed predates those edits, so when there were any, show the human the effective settings from npx -y crysk config instead. Otherwise show the printed summary, including any Changed and Kept existing lines: on a re-run (for example --force to refresh an old workflow) only the groups a flag names are overwritten, and keys nobody chose stay as the file had them; the workflow keeps its old mode and budget-usd unless --ci-mode or --billing / --budget-usd is passed. In a terminal, every question defaults to the repository's current value. Details: references/ci-admission.md.
Execution Steps
- Inspect repo:
git rev-parse --is-inside-work-tree,git remote get-url origin,gh auth status. - Credential path: Claude-only → skip OpenCode. OpenCode or mix → read `references/opencode-ci.md` and execute it (models per role, one secret per provider, the providers variable).
- Claude secret (if used):
gh secret set CRYSK_CLAUDE_OAUTH_TOKENorCRYSK_CLAUDE_API_KEY(secure input, never print). - Workflow: run the interview above, then
npx -y crysk setup --ciwith its flags. It writes.github/workflows/crysk.yml(or rewrites an existingpr-hero.ymlin place) and the level keys in.crysk/config.json, and its next steps print thegh secret set/gh variable setcommands for the person's~/.crysk/config.json(models, credentials, OpenCode providers); run the ones the human agrees to. Confirmchecks: writeandactions: read, bothpull_requestandissue_commenttriggers, thecrysk-secrets: |block and themodels/credentialslines.--forceif an old template lacks them (an oldcredentialsjob, a missingissue_commenttrigger, orclaude-token/routinglines mean it predates the current workflow). - Review instructions (optional, recommended before the first review): if the default branch has neither a root
REVIEW.mdnor.crysk/gotchas.md, runnpx -y crysk initin the clone; it scaffoldsREVIEW.md(an existing.crysk/gotchas.mdis kept, and noREVIEW.mdis written beside it). The agent writes the facts from the repository it has in context, not from the template: the deliberate oddity that looks like a bug, the invariant enforced outside the diff, the ownership rule a newcomer would break. The hunters and the refuter read the file as facts; the "Not blocking here" section is applied only by the materiality judge (materiality_gate: true, blocking findings only, and only to style, naming, test-hygiene, generated-code and dev-script findings), so fill it only when the human asked for that gate, and delete it otherwise. Delete thehuman-attention-requiredmarker line (Crysk refuses to review while it is there), then commit the file to the default branch. With no file the review runs on the default guidance; an empty or scaffold file fails the runCRYSK-GOTCHAS-MISSING. - Require the check: in branch protection, require the
cryskstatus check (the gate), not thereviewjob. The legacypr-herostatus is no longer posted, so a repository that still requires it is blocked until the rule moves tocrysk. A private repository on GitHub Free cannot require status checks (HTTP 403): report that the gate is advisory there. Withgh, and only after asking the human: read the current protection first (gh api repos/<o>/<r>/branches/<default>/protection), because the PUT replaces all of it; thengh api -X PUT repos/<o>/<r>/branches/<default>/protectionwithrequired_status_checkscontexts["crysk"]. - Advanced settings: write the answers from interview question 5 into
.crysk/config.json(and.cryskignore), includingpost_min_severitywhen they chose a floor other thanwarningandmateriality_gate: trueonly when they said yes; commit both to the default branch, and to any other branch PRs target (CI reads the config from the PR's base branch, so it applies from the next PR after the merge). No `models` or `credentials` key there (the repo parser refuses them).npx -y crysk configto verify. - Verify:
npx -y crysk doctor.git status. Confirm no echoed secret, and when OpenCode is on, that everyopencode:model id inCRYSK_MODELSis oneopencode models <provider>lists and each provider's token is inCRYSK_OPENCODE_PROVIDERS. - Deploy: Offer commit. Open a same-repo test PR (forks skip).
Output Contract
Report:
- Secret status (set or manual link). Names only: which
CRYSK_*secrets exist (gh secret list). Never values. - Models (if set): the
CRYSK_MODELSandCRYSK_CREDENTIALSJSON (no credentials in them), and for OpenCode theCRYSK_OPENCODE_PROVIDERStokens and that each model id matchesopencode models <provider>. - Workflow path (
crysk.yml, or the pre-renamepr-hero.yml; both present means two reviews per PR, delete one) and whetherchecks: write,actions: read, theissue_commenttrigger, thecrysk-secretsblock and themodels/credentialslines are present, with no removed input left. - The review settings summary
setup --ciprinted (level, gate, budget, advanced settings), and which ones the human chose, including the posting floor (post_min_severity) and whethermateriality_gateis on. Confirm repo.crysk/config.jsonhas nomodelsorcredentialskey. npx -y crysk doctor/npx -y crysk configoutcome.- Whether the default branch has a real
REVIEW.mdor.crysk/gotchas.md(nohuman-attention-requiredmarker line), or neither (reviews run on the default guidance). - Whether
cryskis a required check (or only the legacypr-hero, which should move tocrysk), or that the repository cannot require one (private repository on GitHub Free). - Next steps: merge the workflow to the default branch (the comment trigger needs it there), open a same-repo test PR, when to turn off observe-only. If CI skipped, the override is
gh pr comment <n> --body "/crysk review".
References
assets/workflow.yml— the one review workflow (pull_request+issue_commentfor/crysk review).assets/admission-config.example.json— starter.crysk/config.json.references/ci-admission.md— admission keys, modes, rollout, ledger.references/opencode-ci.md— OpenCode secrets and variables, models per role, pin, openai vs deepseek.docs/github-actions.md— full CI integration docs.