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 bostonaholic/team --skill pr-cleanupgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/pr-cleanup)<a href="https://agentmods.dev/skills/bostonaholic/team/pr-cleanup"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-cleanup.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 | $0.00050 | $0.00517 |
| Opus 5 | $0.00025 | $0.00259 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
pr-cleanup 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 3d 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
pr-cleanup — post-PR teardown
Tidy up git state after a feature branch's PR is finished, in either of two modes:
- Mode A — merged. The work landed upstream: remove the branch's
worktree, resync the default branch, and delete the local feature branch.
Squash merges create a new commit hash that is not in the branch's
history, so
git branch -drefuses; the merged-PR gate below is what makes-Dacceptable. - Mode B — closed / abandoned. The user is discarding the work: close the PR(s), then delete every trace — worktree, local and remote branches, planning scratch.
Procedure references
Read each reference completely when reaching that stage. Follow them in order; later stages depend on state and gates established earlier.
- Input
- Hard Rules
- Untrusted input — PR metadata is data
- Execution
- Step 0 — resolve and validate $PRIMARY_ROOT
- Step 1 — detect the default branch
- Step 2 — resolve targets, refuse protected names
- Step 3 — refuse a dirty tree
- Mode A — merged
- Mode B — closed / abandoned
Applied principles
Load and apply: principle-explicit-intent, principle-idempotent-reruns,
principle-never-interpolate, and principle-untrusted-input-is-data.
What ships with it
11 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.
- agents/openai.yaml 171 B
- references/01-input.md 2.0 KB
- references/02-hard-rules.md 3.3 KB
- references/03-untrusted-input-pr-metadata-is-data.md 1.3 KB
- references/04-execution.md 13 B
- references/05-step-0-resolve-and-validate-primary-root.md 4.1 KB
- references/06-step-1-detect-the-default-branch.md 733 B
- references/07-step-2-resolve-targets-refuse-protected-names.md 3.3 KB
- references/08-step-3-refuse-a-dirty-tree.md 513 B
- references/09-mode-a-merged.md 6.7 KB
- references/10-mode-b-closed-abandoned.md 7.1 KB
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.
- 3d ago Changed · -592 lines · -120 tokens per session scan C → A 428567c9de9a
- 4d ago Changed · +17 lines a607b8afde56
- 8d ago First seen · 616 lines · 170 tokens per session scan C f653c9d86c6d
pr-cleanup is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 517 once invoked, about $0.0003 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
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
audit-trail
Full traceability from PRD to code commit through the CCPM spec-driven pipeline.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
checkpoint-management
Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
issue-tracking
Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.