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 oliver-kriska/claude-elixir-phoenix --skill watch-prgit clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenixWrote 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/oliver-kriska/claude-elixir-phoenix/watch-pr)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/watch-pr"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/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/oliver-kriska/claude-elixir-phoenix/watch-pr"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/watch-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02106 |
| Opus 5.5 | $0.00020 | $0.00842 |
| Sonnet 5.5 | $0.00010 | $0.00421 |
| Haiku 4.5 | $0.00005 | $0.00211 |
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 25d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- phx-watch-pr — 89% identical, 203 lines differ
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch PR (Token-Conscious)
Watch a PR's reviews, comments, and CI with a background watcher that wakes Claude ONLY on real events — no foreground sleep loops, no context bloat. The watcher polls quietly in its own process; nothing enters context until something genuinely changed.
Usage
/phx:watch-pr 42 # watch reviews + comments + checks
/phx:watch-pr 42 --checks-only # CI only (delegates to gh pr checks --watch)
/phx:watch-pr 42 --fix # on actionable review, draft fixes too
/phx:watch-pr 42 --codex # + request Codex cloud review, loop until clean
/phx:watch-pr 42 --codex --codex-rounds 2 # cap re-review rounds (default 3)
Iron Laws
- NEVER foreground-poll with
sleepin the session — use the background watcher (Monitor / run_in_background). Foreground polling bloats context and straddles the 5-min cache TTL - Deltas ONLY enter context — never dump full
ghJSON. The watcher emits one-line events; read.claude/watch/pr-{n}.jsonlon demand - Silence is not success — the watcher MUST emit on PR closed/merged, CI failure, repeated gh errors, and watchdog timeout — not just "new comment". A silent watcher looks identical to a hung one
- NEVER auto-post replies or auto-push — hand off to
/phx:pr-reviewfor responses; show drafts and get approval. ONE exception: passing--codexIS the consent to post the@codex reviewtrigger comment (and its per-round re-requests) — nothing else is ever auto-posted - Bound every watch — default MAX_DURATION 3600s (7200s with
--codex); always stop on terminal state. Codex rounds are bounded by--codex-rounds(default 3) — each round costs cloud quota
Workflow
Step 1: Parse Arguments
Extract PR number (from number or URL — URL also yields the repo). Detect
--checks-only / --fix / --codex / --codex-rounds N. Baseline
timestamp = now; events are "new since baseline", so old reviews don't
re-fire.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago Changed · +60 lines · +9 tokens per session 23768add3104
- 1mo ago First seen · 94 lines · 41 tokens per session scan A b7b4cb3261c7
watch-pr is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (570 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 2,106 once invoked, about $0.0002 per session on Opus 5.5. 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
craft-plugin-release
Releasing Craft CMS plugins — tagging, Packagist propagation, GitHub releases, branch promotion, shared-library ordering, history rewrites. ALWAYS load when cutting, preparing, verifying, or debugging a plugin release: bumping a version, dating a changelog, creating or moving a git tag, or checking what Packagist…
git-commit
Turn the working changes into one or more atomic commits with well-written messages. Use whenever the user runs /git-commit or asks to commit their work, wrap up a feature, or "commit what I have.".
git-for-research-code
When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control…
odoo-git-commit
Use when committing Odoo work — before git commit, when a staged diff spans multiple modules or mixes a move with edits, or when writing a commit message or PR body. Covers splitting into one-logical-change commits, the [TAG] module: summary convention, move-then-modify, and terse human messages over AI essays. Invoke…
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.