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 skills/vouchdev/vouch/vouch-propose-from-prnpx skills add vouchdev/vouch --skill vouch-propose-from-prgit clone --depth 1 https://github.com/vouchdev/vouchWrote 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/skills/vouchdev/vouch/vouch-propose-from-pr)<a href="https://agentmods.dev/skills/vouchdev/vouch/vouch-propose-from-pr"><img src="https://agentmods.dev/badge/skills/vouchdev/vouch/vouch-propose-from-pr.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 | $0.00017 | $0.00260 |
| Opus 5 | $0.00009 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
vouch-propose-from-pr 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 4d 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.
What it actually says
/vouch-propose-from-pr
A PR is a decision: someone proposed a change, the team accepted it. The "why" gets compressed into the merge message and forgotten. This command preserves the why as cited claims in the KB.
Steps:
- Parse
$ARGUMENTSas a PR URL or<owner>/<repo>#<num>; default to the most-recently-merged PR you authored. - Fetch the PR title, body, and the merged-commit SHA via
gh. - Register the merge commit as a
kb_register_sourceso subsequent claims can cite it. - Read the diff. For each behavioural change (not formatting / renaming),
draft one
kb_propose_claimwhose text summarises the new invariant the code now upholds, citing the source from step 3. - Propose at most five claims per PR. If a PR is that big, suggest the contributor split it next time.
Do not auto-approve. The KB's review gate is intentional; this command only fills the queue.
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.
- 4d ago First seen · 27 lines · 17 tokens per session scan A ac2dbd40e606
vouch-propose-from-pr is a skill published in the GitHub repository vouchdev/vouch (91 stars, last pushed 12d ago), licensed MIT. It adds 17 tokens to every session and 260 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 skills, from other repositories
openclaw-test-heap-leaks
Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.
feishu-wiki
Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.
obsidian-vault-maintainer
Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.
wiki-maintainer
Maintain the OpenClaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.
memory
Deliberately search, add to, or curate your long-term memory with the memory tool — beyond the automatic recall/capture every turn already does. Use when asked who someone is or what they're working on, when you learn a durable fact worth keeping now, or when your notebook holds stale or wrong entries you should clean…
release-openclaw-maintainer
Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.