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 agentmods add skills/khairold/pibun/close-plannpx skills add khairold/pibun --skill close-plangit clone --depth 1 https://github.com/khairold/pibunWrote 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/khairold/pibun/close-plan)<a href="https://agentmods.dev/skills/khairold/pibun/close-plan"><img src="https://agentmods.dev/badge/skills/khairold/pibun/close-plan.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 | $0.00058 | $0.01509 |
| Opus 5 | $0.00029 | $0.00754 |
| Sonnet 5 | $0.00012 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade C, and why
close-plan scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .plan/ How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close Plan
Close a completed .plan/ directory by persisting valuable information into the project's permanent documentation, then cleaning up. This skill is project-agnostic — it discovers where things should go rather than assuming a fixed structure.
Prerequisites
- A
.plan/directory exists with completed plan files - The plan is fully complete (all phases done) or the human has decided to close it early
Step 1 — Read Plan Files
Read all .plan/ files:
.plan/PLAN.md— completed items, parking lot.plan/MEMORY.md— decisions, gotchas, architecture notes, technical context.plan/DRIFT.md— spec deviations that were accepted.plan/SESSION-LOG.md— skim for any context not captured elsewhere
Step 2 — Extract Persistable Information
Sort everything from the plan files into these categories:
A. Key Decisions
Decisions and their rationale that affect future work on this project. Skip decisions that were phase-specific and no longer relevant.
B. Gotchas & Warnings
Permanent gotchas that will trip up future sessions. Skip phase-specific workarounds that no longer apply.
C. Architecture Changes
Structural changes to the codebase — new packages, changed patterns, new conventions. Only include if the project's architecture docs don't already reflect them.
D. Parked Items
Unchecked items from the Parking Lot section of PLAN.md. These are future work candidates.
E. Accepted Drift
Spec changes from DRIFT.md that were accepted. The project's source of truth (spec, README, architecture docs) should reflect these if it doesn't already.
F. Tensions
Any entries added to .agents/TENSIONS.md during the plan. These already live outside .plan/ — just verify they're present.
Discard (do not persist)
- Session log entries (ephemeral — they served their purpose)
- Completed item checklists (the work is done, the code is the record)
- Phase-specific context that's no longer relevant
- Anything already captured in the repo's permanent docs
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 · 179 lines · 58 tokens per session scan C a5277ad3eaae
close-plan is a skill published in the GitHub repository khairold/pibun (19 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,509 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…