Borrowing it
Nothing to install: this file belongs to adamjgmiller/adamsreview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adamjgmiller/adamsreview/main/CLAUDE.mdgit clone --depth 1 https://github.com/adamjgmiller/adamsreviewWrote 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/instructions/adamjgmiller/adamsreview/claude-md)<a href="https://agentmods.dev/instructions/adamjgmiller/adamsreview/claude-md"><img src="https://agentmods.dev/badge/instructions/adamjgmiller/adamsreview/claude-md/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/instructions/adamjgmiller/adamsreview/claude-md"><img src="https://agentmods.dev/badge/instructions/adamjgmiller/adamsreview/claude-md.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 | $0.03163 | $0.03163 |
| Opus 5 | $0.01581 | $0.01581 |
| Sonnet 5 | $0.00633 | $0.00633 |
| Haiku 4.5 | $0.00316 | $0.00316 |
Grade A, and why
adamsreview CLAUDE.md 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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — operational guide for adamsreview
Read on a fresh session. Procedural how-to for the adamsreview plugin. Reference docs load on demand: docs/state-and-gates.md (state model, score gates, lanes), docs/pipeline.md (phase trees + token-tally semantics), docs/helpers.md (helper inventory). bin/schema-v1.json is the source of truth for artifact shape. docs/archive/ is frozen historical reference — consult only for past-decision rationale.
What this repo is
Build repo for six Claude Code slash commands packaged as plugin adamsreview:
/adamsreview:review [--ensemble]— multi-lens review. Phase 0 preflight → 1 detection (up to 6 parallel lens agents — L2/L5/L6 conditional ontrivial_modeand user-facing flags — plus L7 under --ensemble in non-trivial mode; L7 is a holistic Opus safety net) → 1.5 external-source pooling (Codex CLI + GitHub bot-comment scrape, Sonnet normalizer) → 2 dedup → 3 cheap scoring + gate → 4 validation (Opus deep / Sonnet light chunked) → 5 cross-cutting (deep-lane only) → 5.5 auto-fix-hint generation (Sonnet propose+verify two-pass) for confirmed_manual / confirmed_report / confirmed_mechanical findings ≥60 → 6 finalize + render + publish.--ensembleadds the Codex CLI + PR bot-comment scrape sources./adamsreview:codex-review [--effort low|medium|high|xhigh]— Codex peer to:review. Same phase set (0-6 plus Phase 5.5 auto-fix-hint generation), Codex-driven detection/validation/cross-cutting viabin/codex-poll.sh; Phase 1.5 skipped (no ensemble); Phase 5.5 is Sonnet-driven (validator-agnostic, shared with:review). Same artifact shape (reviewer_sources: ["internal-codex"]) so drop-in for:fix/:add/:walkthrough/:promote. Sonnet shape-fixers per Codex output; Codex tokens billed externally (only Sonnet shape-fixer + normalizer + Phase 5.5 intokens.jsonl). Fail-fast on missing Codex (no Claude fallback)./adamsreview:add— inject external findings (cloud/ultrareviewpaste, Opus once-over, manual finds) into the latest review's artifact. Locate latest → leftover-attempted gate → build candidates (paste-normalizer | structured--file/--line/--claim| mixed) → Sonnet dedup → assign continuing IDs → Phase 4 lane-aware (no Wave 2) → re-publish to existing PR comment./adamsreview:walkthrough [threshold]— interactive driver for findings:fixwould skip (deep-manual, deep-report, full light lane), restricted to effective score ≥ threshold (default 60). Two scope tiers (Qualifying / Full skip set) —pre_existing_reportalways routed to end-of-rungh issue createflow. Step 4.5 batch-accepts findings carryingauto_fix_hint(set by Phase 5.5) before the per-finding loop; per-finding loop skips the briefer sub-agent whenauto_fix_hintis present, reusing the pre-computed hint./adamsreview:fix [threshold] [--granular-commits]— automated fix loop for auto-fixable findings. Phase 7 load + leftover-attempted abort + clean-tree gate + staleness check → 7.5 auto-recommendation preflight (surfacesauto_fix_hintfindings for batch-accept; promotes viahuman_confirmationbypass so Phase 8 picks them up) → 8 per-fix-group agents (no git ops) → 9 post-fix Opus review, revert regressions, commit survivors, appendfix_attempts. Phase 9.pre overlap → reconcile/abort/inspect. Default one combined commit;--granular-commitsdoes one per surviving fix group./adamsreview:promote <id>— metadata-only override. Promotes a single finding to auto-fixable, bypassing Phase 8 lane filter and threshold. Run:fixafter.
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.
- 11d ago First seen · 82 lines · 3,163 tokens per session scan A 651497e340d4
adamsreview CLAUDE.md is an instructions file published in the GitHub repository adamjgmiller/adamsreview (243 stars, last pushed 3mo ago), licensed MIT. It adds 3,163 tokens to every session, about $0.0158 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.