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/feo2x/guided-coding/finish-plannpx skills add feO2x/guided-coding --skill finish-plangit clone --depth 1 https://github.com/feO2x/guided-codingWhat 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 | $0.00029 | $0.00628 |
| Opus 5 | $0.00015 | $0.00314 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
finish-plan 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 2d 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:
- guided-coding-finish-plan — 97% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finish a Plan
Finish the plan named by the user. If none is named, proceed only when exactly one uncommitted plan
draft exists in ai-plans/; otherwise ask for its path.
1. Validate
Read the repository instructions and confirm that:
- The filename is either
YYYY-MM-DD-HHMM-<issue-id>-<kebab-case-description>.mdor, without an issue,YYYY-MM-DD-HHMM-<kebab-case-description>.md. - Variable filename segments contain only lowercase ASCII letters, digits, and single hyphens, and do not start or end with a hyphen.
- The file starts with
# Title, followed by exactly## Rationale,## Acceptance Criteria, and## Technical Details, in that order. - Every acceptance criterion is an unticked task (
- [ ]). - Referenced plan documents exist, and claims about existing source files are accurate. Paths for files the plan intends to create are valid references when identified as planned work.
Report validation failures. Fix them only after the user agrees; the Planning Phase is still open until the plan is committed.
2. Commit and freeze
Inspect git status and the staged diff. Preserve unrelated working-tree and staged changes. Stage
the plan if needed, then use a path-limited commit so the commit contains only the plan file. Verify
the resulting commit's file list before continuing; if it contains anything else, stop and report
the problem without rewriting history. Follow repository commit conventions and do not push. The
successful commit ends the Planning Phase and freezes the plan.
3. Optionally publish the first plan
The first plan for a tracked issue may become that issue's description. Follow-up plans are not published there.
Use the tracker and target project documented by the repository. If neither is documented, infer them only when the git remote and tracker clearly agree, state the inferred target, and ask the user to confirm it. If the project has no tracker, skip this step.
Read the current issue title and description before asking to publish. Explain that publishing replaces the complete issue description. If it is non-empty, show or summarize what would be replaced and require explicit confirmation to overwrite it. Publish the plan body only. For GitHub:
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.
- 2d ago First seen · 63 lines · 29 tokens per session scan A 48dc8491b2fb
finish-plan is a skill published in the GitHub repository feO2x/guided-coding (6 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 628 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 2026-08-31.
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…