Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/mock-server/mockserver-monorepo/commitgit clone --depth 1 https://github.com/mock-server/mockserver-monorepoWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00711 |
| Opus 5 | $0.00009 | $0.00356 |
| Sonnet 5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Follow the COMPLETE pre-commit workflow defined in .opencode/rules/commit-workflow.md. Do NOT skip any steps unless the user explicitly says "skip tests", "skip review", or "just commit".
Validation is mandatory and must be executable where possible. Do not rely only on static inspection.
Parallel session safety is mandatory: commit only files changed in the current session. Never include files you did not edit in this session, and never use blanket staging (git add . / git add -A).
The authoritative steps are in commit-workflow.md; do not re-derive or skip any:
- Classify —
git status --short; identify only files YOU changed this session; classify by category (java/terraform/bash/docker/docs/config/helm/npm/python/ruby/control). Files under.opencode/rules/**,.opencode/agents/**,.claude/agents/**,.opencode/commands/**,.claude/commands/**,.opencode/skills/**,.opencode/plugins/**,.opencode/scripts/**,.opencode/evals/**,opencode.jsonc,.claude/settings*.json, the review constitution, or CI/test gates are the control (AI-component) class — higher-scrutiny (see step 4). - Validate — run category-specific, executable validations:
- Java:
./mvnw test -pl <modules> - Terraform:
terraform fmt -check,terraform validate,terraform plan - Bash:
bash -n <script>and execute in a safe mode (--help/--version/--dry-run) - Docker:
docker buildper changed Dockerfile + a basic smoke command - Helm:
helm lintandhelm template - Website:
bundle exec jekyll build - Docs/config: syntax and link checks
- control: run the evaluation harness in gate mode —
STRICT=1 bash .opencode/evals/run-evals.sh(a regression blocks;STRICT=1also fails closed on a fixture with no recorded baseline, which the lenient form reports asPENDING … OK)
- Java:
- Changelog — if the change is user-facing, add or correct a
## [Unreleased]entry inchangelog.md(MANDATORY); if not user-facing, state explicitly why no entry is needed. - Adversarial review — launch a
review-cheapsubagent (fresh context) on the diff; must return PASS. Control / AI-component changes use the authoritativereview-finaland are gated-approval — present the PASS to the user and get explicit approval before committing (separation of duties; never auto-commit a control change). Cap the review loop at 8 iterations; if it does not converge, record the residual risk and escalate — do not commit. - Commit — only after all gates pass: first run
.opencode/scripts/check-halt.sh commit(if it exits non-zero, stop — an operator halt is in force); then stage files by explicit path (NEVERgit add .) and commit with a descriptive message.
If the user provided additional instructions: $ARGUMENTS
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 27 lines · 17 tokens per session scan A 9cd200764ec4
commit is a command published in the GitHub repository mock-server/mockserver-monorepo (4,957 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17 tokens to every session and 711 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
write-fixtures
../../skills/write-fixtures/SKILL.md.
bench
Refresh model grades (capability + price, from benchlm.ai and OpenRouter) or measure route latency through the proxy. Nothing runs automatically — this is the manual refresh.
status
Show cc-proxy router status — proxy liveness, configured providers, GLM/OpenRouter quota, and recent routing decisions.
bmad-architecture
Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
bmad-agent-dev
Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.