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 SienkLogic/plan-build-run --skill undogit clone --depth 1 https://github.com/SienkLogic/plan-build-runWrote 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/sienklogic/plan-build-run/undo)<a href="https://agentmods.dev/skills/sienklogic/plan-build-run/undo"><img src="https://agentmods.dev/badge/skills/sienklogic/plan-build-run/undo.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 | $0.00019 | $0.01911 |
| Opus 5 | $0.00010 | $0.00955 |
| Sonnet 5 | $0.00004 | $0.00382 |
| Haiku 4.5 | $0.00002 | $0.00191 |
Grade A, and why
undo 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STOP — DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's plugin system. Begin executing Step 0 immediately.
Step 0 — Immediate Output
Before ANY tool calls, display this banner:
╔══════════════════════════════════════════════════════════════╗
║ PLAN-BUILD-RUN ► UNDO ║
╚══════════════════════════════════════════════════════════════╝
Then proceed to Step 1.
/pbr:undo — Safe Commit Reversal
You are running the undo skill. Your job is to help the user safely revert recent PBR-generated commits using git revert (history-preserving), not git reset (destructive).
This skill runs inline (no Task delegation).
Step 1 — Gather PBR Commits
Run:
git log --oneline --no-merges -50
Filter lines matching the PBR commit pattern:
^[0-9a-f]+ (feat|fix|refactor|test|docs|chore|wip|revert)(\([a-zA-Z0-9._-]+\))?:
If no PBR commits found, display:
No PBR commits found in the last 50 commits.
Then exit.
Parse $ARGUMENTS for flags:
--last N: limit to N most recent PBR commits (default 20)--phase NN: filter to commits for a specific phase number (e.g.--phase 55)--plan NN-MM: filter to commits for a specific plan (e.g.--plan 55-02)--range HASH..HASH: preselect a hash range for revert — if provided, skip to Step 5 with that range pre-filled
Phase manifest mode (--phase NN):
When --phase NN is specified, first check for a .phase-manifest.json in the phase directory:
- Resolve the phase directory:
.planning/phases/{NN}-*/ - Check for
.phase-manifest.jsonin that directory - If manifest exists: use
manifest.commitsas the commit list (skip git log scan) - If manifest missing (phases completed before manifest support): fall back to git log scan and filter by scope pattern
Phase manifests are written by completePhase(). Older phases may not have manifests.
Apply filters to the collected PBR commits before proceeding.
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 · 222 lines · 19 tokens per session scan A 9d57dfeaec87
undo is a skill published in the GitHub repository SienkLogic/plan-build-run (17 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,911 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 2026-09-03.
Other skills, from other repositories
plan-pipeline-execute
Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
plan-pipeline-eng-review
Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
generate-tests
Generate comprehensive tests for specified code.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).