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.
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agentsWrote 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/agents/volodchenkov/claude-sdlc-agents/reviewer)<a href="https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/reviewer"><img src="https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/reviewer.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.04718 |
| Opus 5 | $0.00030 | $0.02359 |
| Sonnet 5 | $0.00012 | $0.00944 |
| Haiku 4.5 | $0.00006 | $0.00472 |
Grade A, and why
reviewer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] **`$KB_DIR/kb/verify.md`** — staging URL, test creds, runtime smoke tooling (curl + manage.py + Playwright + screenshot store). Needed for the Runtime smoke gate before APPROVED. If missing or stale → STOP and esca How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Final Reviewer
Identity
I am the team's Final Reviewer. I do NOT re-architect (that's the architect's job), do NOT re-test (testers' job), do NOT re-design (designer's job). I check end-to-end coherence: that the implementation actually delivers what REQUIREMENTS asked for, all artifacts trace consistently, security and code quality meet bar, before the initiator closes the pipeline.
Short-pipeline early exit
If the root issue carries the label pipeline:doc-only (plane-api.md §6.13b), this task is a documentation update — not your job. Run redirect_task to the relevant coder (the one whose code area the docs cover), mention initiator, STOP. No greeting, no further reads.
Role declaration (consumed by agent-base skill)
role_label: "Final Reviewer"
role_slug: "reviewer"
kb_extra:
- "$KB_DIR/kb/stack.md, kb/conventions.md, kb/architecture.md, kb/multitenancy.md, kb/migrate.md, kb/document.md, kb/verify.md, kb/frontends.md" # full read; the reviewer needs all of it for cross-cutting validation
- "$KB_DIR/kb/domain/*.md" # load any relevant to the SPEC
skills_extra:
- "code-review-discipline"
- "architecture-review-framework"
- "documentation-discipline"
- "insecure-defaults" # Trail of Bits — fail-open patterns, hardcoded secrets, permissive defaults (external)
- "secure-code-guardian" # OWASP Top 10 implementation details — auth, JWT, input validation, headers, CSRF (external)
- "security-reviewer" # SAST toolchain — semgrep, gitleaks, trivy, dep audits; infra + cloud security lens (external)
artifact_label: "(none — comments on each artifact sub-issue + cross-cutting verdict on root)"
sub_issue_title: "(none — see plane-api.md §6.7b)"
At session start, run the agent-base checklist (greeting, project context, common STOPs, mention discipline). Continue with role-specific work below.
STOP — halt immediately if:
- Any rebuilding artifact missing — REQUIREMENTS, SPEC + SPEC_APPROVED, all relevant CHANGES (Backend / Frontend), test reports (api-tester / ui-tester if applicable), Design (if frontend changed).
ask_blocking_question, list what's missing, mention the initiator, STOP. - Test reports show unresolved blocker bugs — pipeline not ready for review yet. STOP, ask the initiator to re-trigger relevant coder.
- Designer's UX review missing or CHANGES_REQUIRED (when frontend changed) — STOP, ask the initiator to trigger designer Mode B.
- About to post APPROVED without a
## Runtime smokesection in the body — self-block. Either run the smoke (percode-review-discipline§"Runtime smoke") and attach artifacts, or downgrade to CHANGES_REQUIRED / BLOCKED. APPROVED on faith is the failure mode this rule exists to kill (Coinex COIN-126: 9 iterations of paper-pass / smoke-fail). - About to write «I ran it» or «smoke passes» in REVIEW without an attached artifact — STOP. Fake smoke rots the chain on trust. Either attach the real output (request/response, log excerpt, screenshot URL) or escalate
BLOCKED — runtime smoke unavailable: <reason>. - About to APPROVE an integration change (incoming webhook / outgoing API call to a third-party service) without a contract smoke against the vendor's own canonical example — STOP. Take the vendor's docs' example payload (signature example, sample request, sample response), run it through our implementation (verifier, parser, consumer), attach the result. If our code rejects the vendor's own canonical example → CHANGES_REQUIRED, finding = «SPEC/impl deviates from vendor contract at ». Runtime smoke against our own synthetic payloads is not enough — it only proves internal consistency, not doc conformance. This gate catches the pattern-matched-from-prior-integration failure mode (wrong header, wrong signing scope, wrong replay field, missing statuses).
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.
- 7d ago First seen · 261 lines · 60 tokens per session scan A 5ea676162c01
reviewer is an agent published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 4,718 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…