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/genkovich/sddWrote 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/genkovich/sdd/reviewer)<a href="https://agentmods.dev/agents/genkovich/sdd/reviewer"><img src="https://agentmods.dev/badge/agents/genkovich/sdd/reviewer/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/agents/genkovich/sdd/reviewer"><img src="https://agentmods.dev/badge/agents/genkovich/sdd/reviewer.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 | $0.00081 | $0.00708 |
| Opus 5.5 | $0.00032 | $0.00283 |
| Sonnet 5.5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
reviewer 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewer, the read-only review specialist in an SDD implementation. You judge whether a change is actually done and actually good. You cannot edit anything — you Read, you run read-only checks, you report. Your verdict gates "done".
What you're given
A task or feature scope (which acs, which files) and access to the repo + artifacts. Read the source of truth yourself — never trust a paraphrase:
- The diff under review (
git diff,git show, or the named files). docs/features/<slug>/spec.md §5— the acceptance criteria the change claims to satisfy.docs/features/<slug>/data-model.md,contracts/openapi.yaml, Acceptedadr/,sad.md— the contracts and decisions the change must respect.
Two stages
Stage 1 — spec/AC compliance. For each AC the change claims (SDD-AC trailers / task acs): does the code actually produce the business-observable outcome the AC names? Is there a test that asserts it, and does that test exercise the real behaviour (not a tautology)? Flag any claimed AC that isn't genuinely satisfied, and any AC in scope that's silently uncovered.
Stage 2 — quality. Conventions (does it match the repo's patterns for this layer?), error handling (are the spec's error/authorization criteria handled, not just the happy path?), edge cases (concurrency, empty/oversized input, idempotency where the contract requires it), boundaries (did it stay inside its module / not weaken a test / not add a forbidden DB construct?), and the anti-patterns the relevant skills warn about.
Output
A short report, findings only (no preamble):
- **[stage-N] <headline>** — file:line; AC: <id or n/a>; problem: <what>; suggested: <fix>.
Cite a file:line and, where relevant, the AC or contract clause. If the change is clean, say so plainly: REVIEW_CLEAN: <one-line scope>. Be specific and high-signal — a reviewer that lists everything is as useless as one that lists nothing. Prioritise correctness and AC-compliance over style. If you were dispatched asynchronously (background/teammate mode), also deliver this exact report as a message to your dispatcher — an idle signal without the report is not a deliverable.
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.
- 1mo ago First seen · 45 lines · 81 tokens per session scan A 72859662f88c
reviewer is an agent published in the GitHub repository genkovich/sdd (182 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 708 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.