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/promote)<a href="https://agentmods.dev/commands/adamjgmiller/adamsreview/promote"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/promote/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/promote"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/promote.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 | $0.00028 | $0.02367 |
| Opus 5 | $0.00014 | $0.01184 |
| Sonnet 5 | $0.00006 | $0.00473 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
promote scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote a single finding from the most recent /adamsreview:review on this
branch to disposition=confirmed_mechanical, recording full provenance in
human_confirmation so /adamsreview:fix will pick it up on its next
run.
Read fragments/_prelude-shared.md before proceeding — it lists
rules that apply to every step below (sub-agent return handling,
helper-script error-as-prompt).
Arguments
<finding_id>(required, positional) — matches^F[0-9]+$. The id shown in the artifact's PR comment orartifact.md.--reason "..."(optional) — free-form justification recorded inhuman_confirmation.reason. Audit-focused ("why I promoted"). If omitted, you'll be prompted.--fix-hint "..."(optional) — free-form steering instruction recorded inhuman_confirmation.fix_hintand surfaced to the Phase 8 fix-group agent. Instruction-focused ("how to fix"). Use this when the claim is ambiguous about which side of a code/text mismatch to change (e.g. "update the docstring to match the code; do not modify the code"). Auto-prompted when omitted on a light-lane finding (one whosevalidation_resultis null) so the fix agent isn't left guessing. Deep-lane findings can still pass it explicitly to override the validator'sfix_proposal.approach.--force(optional) — required when promoting a finding currently atdisposition=disproven(validator found positive evidence it's wrong). Without--force, disproven findings reject promotion with a user-visible message pointing to the validator's conclusion.--defer-publish(optional) — skip steps 7 (re-render), 8 (re-publish to PR), and 10 (user-visible summary). The artifact patch and trace entry still land. Useful for scripted promote loops where render+publish should run once at the end rather than per-iteration;/adamsreview:walkthrough(§28) uses this internally. When set, the caller is responsible for runningartifact-render.pyandartifact-publish.shafterward.
Does NOT run /adamsreview:fix for you. Run it yourself when you're
ready to apply promoted findings.
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.
- 12d ago First seen · 238 lines · 28 tokens per session scan A 2993361d921d
promote is a command published in the GitHub repository adamjgmiller/adamsreview (243 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,367 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ 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.