pr-watch-mechanics

pr-watch-mechanics is a skill for Claude Code, Codex from bostonaholic/team. It costs 36 tokens per session (674 once invoked), scanned A, original, MIT.

A bounded polling loop for repeatedly checking a condition while a pull request is being watched. A pull request is a proposed code change awaiting review or merging.

In plain words
What is it for?
Use it as the timing and handoff mechanism for pull-request watch loops used by authors or reviewers.
Why use it?
It prevents watch jobs from running forever and specifies when to poll immediately, wait between checks, and hand work to another step.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present. Also seen: mentions Claude Code.

Part of the team plugin — 93 skills, 13 agents, 2 hooks shipped together

Good fit Use it as the timing and handoff mechanism for pull-request watch loops used by authors or reviewers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bostonaholic/team/pr-watch-mechanics
Install

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.

Any agent
npx skills add bostonaholic/team --skill pr-watch-mechanics
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 93 skills, 13 agents, 2 hooks.

Wrote 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.

agentmods badge for pr-watch-mechanics

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-mechanics/github.svg)](https://agentmods.dev/skills/bostonaholic/team/pr-watch-mechanics)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/pr-watch-mechanics"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-mechanics/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.

agentmods 80×15 button for pr-watch-mechanics

Your own site · 80×15
<a href="https://agentmods.dev/skills/bostonaholic/team/pr-watch-mechanics"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-mechanics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00674
Opus 5 $0.00018 $0.00337
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00004 $0.00067

Measured 6d ago against content hash 5f782a8b59ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-watch-mechanics 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.

skills/pr-watch-mechanics/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR watch mechanics

The cycle timing, bound, and handoff every PR watch loop runs. A consuming skill owns what each cycle does; this skill owns how the loop is paced, bounded, and ended. pr-watch-as-author and pr-watch-as-reviewer both load it.

A consumer binds three slots and nothing else:

Slot What the consumer supplies
Poll command The command its own poll step runs.
Cycle-0 subject What an already-satisfied condition at arm time means for it.
Handoff state The fields its handoff prints.

The loop is bounded, never infinite

  • Cycle 0 polls immediately — the condition that already holds at arm time is handled at once, on the consumer's cycle-0 subject.

  • Each later cycle is one backgrounded Bash call that sleeps the interval and then runs the consumer's poll command, so the cycle costs one turn and the poll output is in hand when the harness reports the call:

    sleep 1860; <the poll command>
    

    Run it with run_in_background: true. Per principle-non-blocking-waits, a foreground wait is killed at the harness ceiling (600 s in Claude Code) and spends a turn per fragment.

  • Soft cap: 3 cycles (~90 minutes). At cycle 3, if nothing has stopped the loop already, end the interactive session — do not sleep again. Print a handoff: the consumer's handoff state and the exact command to resume the watch as a scheduled headless job — the scheduled pr-watch job (~/dotfiles/bin/pr-watch.sh, run from launchd). Re-arming the interactive loop happens only on explicit user request; the loop does not re-arm itself.

  • The bound is the invariant, not the interval: 3 cycles at ~31 minutes. Where a harness offers no background execution, say so and chunk the wait into foreground sleeps sized under that harness's ceiling — the cycle count is what must hold.

The cap convention is principle-bounded-loops: declare the bound with the loop; hitting it is a loud, terminal, reported outcome.

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 6d ago First seen · 68 lines · 36 tokens per session scan A 5f782a8b59ca

Subscribe to this mod's changes

pr-watch-mechanics is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 674 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 2026-09-05.