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 commands/ucsandman/dashclaw/apply-self-reviewgit clone --depth 1 https://github.com/ucsandman/DashClawWrote 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/ucsandman/dashclaw/apply-self-review)<a href="https://agentmods.dev/commands/ucsandman/dashclaw/apply-self-review"><img src="https://agentmods.dev/badge/commands/ucsandman/dashclaw/apply-self-review.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 5.1 | $0.00047 | $0.00978 |
| Opus 5 | $0.00023 | $0.00489 |
| Sonnet 5 | $0.00009 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
apply-self-review 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 6d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the apply stage of DashClaw's self-improvement loop. The weekly /memory-self-review job writes a PROPOSAL; you turn the approved items into real edits — safely. You are the action counterpart to that read-only review: you act, but you keep the human gate exactly where risk lives.
Mode = $1 (default: safe).
1. Load the proposal
Read C:\Projects\DashClaw\docs\superpowers\memory-self-review-PROPOSAL.md. If it's missing or empty, say so and stop — nothing to apply. If it looks stale, check the tail of C:\Users\sandm\.claude\jobs\memory-self-review.log to confirm the latest run.
2. Classify every proposal item
- SAFE (auto-appliable): additive, reversible, doc/memory only — appending a documented gotcha/lesson line to an existing CLAUDE.md section; demoting/trimming/moving a MEMORY.md index entry; fixing a stale pointer or count in a doc/memory file. No code behavior change, no deletion of meaning, nothing touching settings/hooks/CI/git-config/deps/schema/auth/billing.
- NEEDS-CONFIRM (never apply without an explicit go): any change to code,
settings*.json, hooks, CI,.gitattributes/git config, dependencies, schema/migrations; deleting or rewriting the meaning of an existing rule; anything touching auth/billing; or anything you are unsure about. When in doubt → NEEDS-CONFIRM.
Editable targets and their paths:
- Project CLAUDE.md:
C:\Projects\DashClaw\CLAUDE.md - Global CLAUDE.md:
C:\Users\sandm\.claude\CLAUDE.md - Memory index + files:
C:\Users\sandm\.claude\projects\C--Projects-DashClaw\memory\
3. Apply
- Before editing ANY file, back it up once:
<file>.bak-apply-<YYYYMMDD>(skip if it already exists today). - Grep the target section first — never insert a line that's already present (idempotent).
safe(default): apply every SAFE item into its named section, matching the proposal's wording. Then LIST the NEEDS-CONFIRM items with their exact proposed edit and STOP — do not apply them.all: apply SAFE items, then for each NEEDS-CONFIRM item restate the exact change and apply it (only when a human is present and signalledall).<item numbers>: apply exactly those items regardless of class — the number IS the explicit go.
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.
- 6d ago First seen · 42 lines · 47 tokens per session scan A f856f11af976
apply-self-review is a command published in the GitHub repository ucsandman/DashClaw (297 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 978 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 commands, from other repositories
code-review
Provide a code review for the given pull request.
blackboard
Read or write a Network-AI blackboard key (shared multi-agent state).
squash
Rebuild a feature branch into clean conventional commits while preserving its exact final tracked tree.
resolve-dependabot-prs
Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.
update-vocabulary
Analyze confirmed Ion vocabulary changes, update the registry, and regenerate its index without renaming code.
release
Create a new release for the Starpod workspace.