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 skills add 0xmariowu/builders-dont-cry --skill watch-prgit clone --depth 1 https://github.com/0xmariowu/builders-dont-cryWrote 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/0xmariowu/builders-dont-cry/watch-pr)<a href="https://agentmods.dev/skills/0xmariowu/builders-dont-cry/watch-pr"><img src="https://agentmods.dev/badge/skills/0xmariowu/builders-dont-cry/watch-pr/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/skills/0xmariowu/builders-dont-cry/watch-pr"><img src="https://agentmods.dev/badge/skills/0xmariowu/builders-dont-cry/watch-pr.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 | $0.00082 | $0.01583 |
| Opus 5 | $0.00041 | $0.00792 |
| Sonnet 5 | $0.00016 | $0.00317 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
watch-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 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/watch-pr — operate the v7 watch daemon
The v7 architecture has a single long-running pr-watch-daemon polling
every active PR. The PostToolUse hook auto-registers PRs after push, so
the day-to-day flow needs zero AI involvement. This skill exposes the
manual control surface for cases the hook does not cover.
v7 automatic chain (you do not participate)
git push / gh pr create
↓
PostToolUse hook (auto-watch-on-push.sh)
→ bash pr-watch-register.sh <repo> <pr> "<trigger>"
↓
state-dir/active/<slug>-<pr>.meta written
ensure-daemon spawns pr-watch-daemon if not already running
↓
daemon polls every 30s (gh pr view + GraphQL reviewThreads)
state change → emit baseline / state_change / merged / etc.
→ ${BDC_HOME:-$HOME/.bdc}/pr-events.jsonl
↓
[next user prompt, any session]
↓
UserPromptSubmit hook (pr-events-flush.sh)
→ renders 📊 dashboard with [action_tag] per row
→ AI sees the dashboard at the top of the next prompt
Manual operations (the skill's job)
/watch-pr <N> — start watching PR #N in the current repo
unset GITHUB_TOKEN
repo=$(gh repo view --json nameWithOwner -q .nameWithOwner)
bash ${BDC_HOME:-$HOME/.bdc}/scripts/pr-watch-register.sh "$repo" <N> "manual /watch-pr"
pr-watch-register.sh writes the meta file and ensures the daemon is
running. The daemon will pick the PR up on its next tick (≤ 30s).
Idempotent — safe to call when the PR is already being watched.
/watch-pr <repo> <N> — start watching a PR in any repo
bash ${BDC_HOME:-$HOME/.bdc}/scripts/pr-watch-register.sh example/repo 187 "manual /watch-pr"
/watch-pr stop <N> (or <repo> <N>) — permanently stop watching this PR
unset GITHUB_TOKEN
repo=$(gh repo view --json nameWithOwner -q .nameWithOwner)
bash ${BDC_HOME:-$HOME/.bdc}/scripts/pr-watch-stop.sh "$repo" <N> "<reason>"
Writes state-dir/ignored/<slug>-<pr>.json, cleans every stale state
file (active meta / fingerprint / post-merge / cooldown / last_change /
per-PR lock), emits a watch_ignored event. The daemon will not
re-discover this PR until you run unignore. Use this when the user
says "别盯了 / 停掉 / 转人工 / 这个 PR 我自己来".
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 · 136 lines · 82 tokens per session scan A c1d8857ae56c
watch-pr is a skill published in the GitHub repository 0xmariowu/builders-dont-cry (4 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,583 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…