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/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/commands/adamjgmiller/adamsreview/add)<a href="https://agentmods.dev/commands/adamjgmiller/adamsreview/add"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/add/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/commands/adamjgmiller/adamsreview/add"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/add.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 | $0.00049 | $0.12119 |
| Opus 5 | $0.00024 | $0.06059 |
| Sonnet 5 | $0.00010 | $0.02424 |
| Haiku 4.5 | $0.00005 | $0.01212 |
Grade C, and why
add scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf -- "$scratch" How it starts
The opening of the file, as written. The whole thing — 1,148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command is additive — it does NOT re-run Phase 1 detection,
Phase 2 dedup against the original lens output, Phase 5 cross-cutting
analysis, or any fix loop. To re-derive everything from the diff, run
/adamsreview:review (which overwrites the artifact).
Arguments
Two invocation shapes — pick whichever fits the input:
- Free-form paste mode (default): all positional
$ARGUMENTStokens are joined with spaces and treated as the paste body. A Sonnet "paste normalizer" sub-agent extracts one or more candidates from the text. Works for chat dumps, review summaries, multi-bug lists, etc. - Structured one-shot mode: when ALL three of
--file,--line, and--claimare present, skip the normalizer and build a single candidate inline. Useful for hand-crafted findings where the reviewer already knows file/line/claim and wants to skip the LLM round-trip.
Optional flags:
--impact <type>— one ofcorrectness,security,ux,policy,architecture. Setsimpact_type(and thusvalidation_lane) on every emitted candidate. Defaultcorrectness. In paste mode this overrides the normalizer's per-candidate guess; useful when the reviewer knows the input is "all security."--no-dedup— skip the dedup pass (§step 5). Useful when the reviewer is confident the input is fresh, or when the artifact has many findings and the dedup call would be expensive.
Read fragments/_prelude-shared.md before proceeding — it lists
rules that apply to every step below (sub-agent return handling,
helper-script error-as-prompt).
Build a TaskList that mirrors the numbered steps below. Mark each
in_progress when starting, completed when done.
Execution
Work through the steps in order. Capture each named variable into your working context.
1. Parse arguments
Parse $ARGUMENTS:
- Walk tokens left-to-right looking for the optional flags
(
--file <path>,--line <N>,--claim "...",--impact <type>,--no-dedup). Strip surrounding quotes from--claim's value. - All non-flag tokens (and tokens not consumed as flag values) join
with single spaces into
paste_body(may be empty).
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 · 1,148 lines · 49 tokens per session scan C 25479b55fb6e
add is a command published in the GitHub repository adamjgmiller/adamsreview (243 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 12,119 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.