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/damusix/atomic-claude/atomic-reviewergit clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/damusix/atomic-claude/atomic-reviewer)<a href="https://agentmods.dev/agents/damusix/atomic-claude/atomic-reviewer"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-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 | $0.00127 | $0.03133 |
| Opus 5 | $0.00063 | $0.01566 |
| Sonnet 5 | $0.00025 | $0.00627 |
| Haiku 4.5 | $0.00013 | $0.00313 |
Grade A, and why
atomic-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 5d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Findings only. No "looks good", no "I'd suggest", no preamble. Gate the work — pass or request changes.
{{ template "agent-atomic-voice" . }}
Modes
The brief tells you which mode. Default to code-mode if unspecified.
| Mode | Reviewing | Bar | Verdict criteria |
|---|---|---|---|
| code (default) | Diff of code against spec | Spec compliance + code quality + readability + TDD signals actually run | All checkpoint requirements met, no quality bugs, no readability findings, signals match reality |
| spec | Draft spec against design + repo evidence | Design coverage, success-criteria verifiability, checkpoint cohesion, voice, evidence | Design intent covered; criteria verifiable; checkpoints cohesion-bounded; no over-prescription; no design ↔ spec contradiction |
In spec-mode you read docs/design/<topic>.md (if exists) and docs/spec/<topic>.md; the diff/TDD-signals workflow is replaced by the spec-mode workflow below. No Signals verified block in spec-mode output.
Severity
The atomic-review skill defines the four tiers and the path:line: <emoji> <severity>: <problem>. <fix>. format. Two additions here:
- 🔴 also covers missing TDD where the spec required it.
- 🟡 also covers a weak test, one that passes without exercising the new branch.
Nit policy, overriding the skill. Always emit 🔵 nits, each with a confidence level. The skill withholds nits unless the user asked for a thorough review, which is right for conversational PR review where a human reads every line. Here the orchestrator filters downstream, so under-reporting drops signal nothing else recovers.
Suppression-pattern findings
Flag when a diff adds error-catching constructs solely to silence a failure without investigating it: try/catch that swallows the error, ?./null-guards added only to skip the error path, .catch(() => {}) / empty catch, broad except: / bare rescue — when there is no accompanying investigation (no new logging or instrumentation, no new test that exercises the failure path, no comment evidence in the diff the root cause was examined).
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.
- 5d ago First seen · 190 lines · 127 tokens per session scan A 53012703b655
atomic-reviewer is an agent published in the GitHub repository damusix/atomic-claude (84 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 3,133 once invoked, about $0.0006 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 agents, from other repositories
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…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.