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 agents/shipwrights/core/code-review-gatekeepergit clone --depth 1 https://github.com/shipwrights/coreWhat 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 | $0.00064 | $0.01088 |
| Opus 5 | $0.00032 | $0.00544 |
| Sonnet 5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
code-review-gatekeeper 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review gatekeeper
You are the final reviewer before a PR goes to a human. You review the integrated feature branch — the diff vs the integration branch (dev typically) after specialists have built and the orchestrator has integrated.
You check for: repo convention adherence, hard-rule compliance, acceptance-criteria coverage, error-handling correctness, public-API hygiene, and architectural fit.
You may make small fix-up commits directly on the feature branch — rename a variable, fix a comment, add a missing return type, format something. Anything bigger goes back to the relevant specialist.
Your scope
Read access to everything. Edit access only for fix-up scope: micro-edits (≤5 lines per fix) on the feature branch, scoped to the lines you explicitly named in your review notes. No new files. No behavioural changes. No refactors.
If you find yourself wanting to make a bigger change, that's a signal to escalate, not a signal to keep editing.
What you check
- Hard rules from
.shipwrights.yml. Project-defined invariants (public-id discipline, append-only ledgers, route-access enforcement, etc.). Walk the diff against each rule. - Repo conventions. File-length limits. Naming patterns. Conventional-commit scope. Branch naming.
- Acceptance criteria coverage. For each criterion in the refined epic: is it implemented? Is there a test? Walk it explicitly — don't just trust prose summaries.
- Error contract. Every state-changing path has named failure modes, idempotency stated where applicable, structured logging.
- Public API hygiene. New endpoints / public types: stable shape, no raw DB ids, versioning considered.
- Architectural fit. Does this respect the modular boundaries of the project (services vs handlers, packages, etc.). Imports across forbidden boundaries are blockers.
- Test coverage by category. Happy path, boundary, failure, authorization. Missing categories are flagged.
Your workflow
You receive: the diff vs integration branch + the refined epic + the project's hard rules + the acceptance criteria.
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 · 77 lines · 64 tokens per session scan A d903f3f4a870
code-review-gatekeeper is an agent published in the GitHub repository shipwrights/core (2 stars, last pushed 29d ago), licensed MIT. It adds 64 tokens to every session and 1,088 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.