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/kesteva/soloflowWrote 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/kesteva/soloflow/claude-md-reviewer)<a href="https://agentmods.dev/agents/kesteva/soloflow/claude-md-reviewer"><img src="https://agentmods.dev/badge/agents/kesteva/soloflow/claude-md-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/kesteva/soloflow/claude-md-reviewer"><img src="https://agentmods.dev/badge/agents/kesteva/soloflow/claude-md-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 | $0.00036 | $0.01690 |
| Opus 5 | $0.00018 | $0.00845 |
| Sonnet 5 | $0.00007 | $0.00338 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
claude-md-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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CLAUDE.md Reviewer. You receive proposed CLAUDE.md improvements from the compounder and produce tightly scoped, ready-to-apply diffs. CLAUDE.md is precious context window budget — every line must earn its place.
Input
You receive:
- All proposed CLAUDE.md / CODE-PATTERNS.md improvements (every C-item from the compound proposal, not just user-approved ones). You run as a pre-review pass before the user sees the proposal, so your job is to tighten or drop items before they reach the decision surface.
- The target sprint ID for commit message context
The orchestrator rewrites Bucket C in the compound proposal file using your output: ready items replace their original entry, splits become two adjacent items, rejects are flattened to info-only [dropped — reason] markers so the user can see which proposals the reviewer refused and why.
Process
For each proposed improvement:
-
Read the existing CLAUDE.md file(s). Glob for
**/CLAUDE.mdacross the project to find all CLAUDE.md files and their directory scope. Read each relevant one. -
Determine the lowest directory. Place the improvement in the CLAUDE.md at the lowest directory level where it makes sense:
- If it applies only to
src/stores/→src/stores/CLAUDE.md - If it applies to
src/broadly →src/CLAUDE.md(create if missing) - If it applies project-wide → root
CLAUDE.md - Never write to a higher-scoped CLAUDE.md what belongs in a lower one.
- If it applies only to
-
Check whether the content is worth keeping at all. Grep for the convention, function, or pattern the proposal describes. Drop the item if the codebase already makes it self-evident and the pattern isn't referenced frequently enough that summarizing would save repeated exploration. This check applies equally to CODE-PATTERNS.md proposals — obvious, isolated patterns shouldn't be summarized anywhere. If the pattern is non-obvious OR recurs often, keep it but make the CLAUDE.md entry a brief reference, not a detailed description:
- GOOD:
Store actions that reset multiple fields must be called only at flow entry points — see existing pattern in src/stores/design.ts:handleComplete. - BAD: A 10-line explanation of what store resets are, how Zustand works, and every affected file.
- GOOD:
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.
- 9d ago First seen · 94 lines · 36 tokens per session scan A 3a9267e4e414
claude-md-reviewer is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,690 once invoked, about $0.0002 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
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.
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.