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 skills add synaptiai/synapti-marketplace --skill code-review-methodologygit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/synaptiai/synapti-marketplace/code-review-methodology)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/code-review-methodology"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/code-review-methodology/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/code-review-methodology"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/code-review-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00107 | $0.01297 |
| Opus 5.5 | $0.00043 | $0.00519 |
| Sonnet 5.5 | $0.00021 | $0.00259 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
code-review-methodology 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 19d ago.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Methodology
Contract
Iron law: verify it works before verifying it is good; never review quality on code that misses the acceptance criteria. Required by /flow:review, /flow:pr, code-reviewer, security-reviewer. Returns a P1/P2/P3 finding set (references/finding-schema.md), a requirements map, and APPROVE, COMMENT or REQUEST_CHANGES. Skips: Stage 2 when Stage 1 finds >3 unmet criteria; on the 3rd+ cycle, only new P1s.
Two-stage review
Stage 1, spec compliance. Give each acceptance criterion one status: Met (implemented and testable), Interpreted (ambiguous; one reading implemented), Partially Met, Not Addressed. If Stage 1 fails, stop.
Stage 2, code quality, in priority order: security, correctness, performance, maintainability. Never flag maintainability while security or correctness findings stand.
6-facet review
Stage 1 on the main thread; facets fan out in parallel:
| Facet | Focus | Agent / Skill |
|---|---|---|
| Security | OWASP top 10, secrets, authz, input validation | security-reviewer |
| Quality | Logic, edge cases | code-reviewer |
| Conventions | Commit, branch, PR format | convention-checker |
| Tests | Coverage, quality commands, adequacy | test-runner |
| Error handling | Unhandled errors, silent failures | error-handler-inspector |
| Claim verification | Self-review claims vs files | holdout-validation |
Tests facet rule: derive the expected behavior from the spec BEFORE reading the tests, then check each expected value and input against it; an expectation copied from the implementation confirms nothing (references/test-review-checklist.md).
Synthesis
- Deduplicate by
file:line, keeping the highest priority- Optionally, a System One provider is asked whether two remaining findings in one file, whose reviewer lists differ, describe the same defect (
review.dedup, off by default;references/system-one.md). In on mode a confident yes merges them under the finding with the highest priority, listing every location and reviewer. A security finding, a LOW finding paired with a HIGH or MEDIUM one, and two findings with the same reviewer list are never merged.
- Optionally, a System One provider is asked whether two remaining findings in one file, whose reviewer lists differ, describe the same defect (
- Order P1, P2, P3 by file
- Count per priority; counts must match the
Finding | Suggested Fixrows (references/finding-schema.md)
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.
- 19d ago Changed · +1 lines d43fc47d440c
- 1mo ago Changed · +9 lines a367ebad2c3b
- 1mo ago Changed · -4 lines 3ae07630696e
- 1mo ago Changed · -109 lines · +17 tokens per session 50a0f75e1c4f
- 1mo ago First seen · 188 lines · 90 tokens per session scan A 9396aa376e70
code-review-methodology is a skill published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,297 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
backlog
Seed a backlog from the project's documents: the Product Owner reads docs/ (plus the constitution and ROADMAP.md), proposes an ordered list of feature-sized items each traced to a source section, the user edits the list, and on explicit confirmation each item is filed as a GitHub issue that /story-time can import. Use…
architect
Produces Alon's design-doc system before code: SOURCEOFTRUTH.md, ARCHITECTUREROADMAP.md, TODOWORKFLOW.md, CLAUDE.md, plus a modular docs/architecture set for larger projects. Model first: data and invariants before framework, every invariant enforced at two boundaries, failure paths designed as deliberately as happy…
next-steps
Have the Product Owner survey the project's current state — shipped features, in-flight work, open findings, standing goals — and propose one concrete next feature ready to hand to /story-time or /spark. Use when the user has no idea in hand and asks "what should we build next", when a loop just closed and the next…
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
increment
Start the Act phase of the SPARK loop: build the increment strictly following the approved plan, task by task, with progress tracked in the plan. Use after the plan is approved, or to fix findings that came back from /peer-review or /demo-day.