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 ayberkcansever/ai-skills --skill execute-plangit clone --depth 1 https://github.com/ayberkcansever/ai-skillsWrote 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/ayberkcansever/ai-skills/execute-plan)<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/execute-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/execute-plan/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.
<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/execute-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/execute-plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.06066 |
| Opus 5.5 | $0.00017 | $0.02426 |
| Sonnet 5.5 | $0.00009 | $0.01213 |
| Haiku 4.5 | $0.00004 | $0.00607 |
Grade A, and why
execute-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 1mo 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Plan
Overview
Load plan, review critically, execute ready tasks in waves in the ticket venue (this checkout if already on the ticket branch, else a worktree), run the verifications the plan specifies, report when complete.
Announce at start: "I'm using the execute-plan skill to implement this plan."
Invariants — read first, re-read after any context compaction
- Review the plan critically first.
- Follow plan steps exactly; don't skip verifications.
- Commit with explicit paths only (or the repo's commit helper); never
git add .. - Stop when blocked — don't guess.
- Execute in this checkout when already on the ticket branch; otherwise in the ticket worktree. The venue's plan copy is the live one.
- Dispatch every legal task in a wave; fan in serially — commit, sync docs, tick, one task at a time.
- This skill runs the review gate as Step 4.4. Do not also invoke
/thermo-nuclear-code-quality-reviewunless the user edited code afterVerdict: ship./graph-retrois post-merge, not the next implement step. - Long runs get compacted; this file and the plan live on disk. If the
conversation was summarized, or you cannot recall a rule verbatim, re-read
this file and the plan header's
For agentic workersblock before the next action — never act from a summary of them.
The Process
Step 1: Load and Review Plan
- Read the plan file (the one produced by write-plan or interview-plan).
Infer
<TICKET-ID>from the plan path first, then an existing ticket worktree, then the current branch, then ask once — the user's checkout may be onmainor another ticket. If the user did not say which file, search in this order:- already-listed worktree for this ticket (it is live — prefer it)
docs/features/<TICKET-ID>/(tracked)docs/plans/<TICKET-ID>/(gitignored WIP)- Legacy flat
docs/plans/*.mdordocs/PLAN_*.mdIf both tracked and WIP copies exist in the same checkout, diff them; if they diverge, ask which is active — never silently prefer the promoted copy over newer WIP. Record the absolute path of the user's checkout — Step 2 copies from there only when the worktree does not already have the WIP docs.
- Review it critically — identify any questions, gaps, or concerns before
touching code. A plan whose header links a spec but carries no
**Audit:** cleanline: if an interview spec exists for this ticket, the Audit Pass was interrupted — confirm before executing. If there was no interview (standalone write-plan), missing audit is expected — still confirm once, then proceed. Do not treat both cases as "interrupted interview". - If concerns: raise them with the user before starting. Resume / stash / TodoWrite wait until Step 2 has the live plan.
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.
- 1mo ago Changed · +2 lines 64b7e3e7a65f
- 1mo ago Changed · +17 lines 4bad6d3dc036
- 1mo ago Changed · +27 lines · -14 tokens per session 99534ae1e655
- 1mo ago Changed · +3 lines 7f5ed7fdffe6
- 1mo ago Changed · +3 lines 1bb607180635
- 1mo ago First seen · 390 lines · 57 tokens per session scan A 2ff716c86cac
execute-plan is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 43 tokens to every session and 6,066 once invoked, about $0.0002 per session on Opus 5.5. 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
pn-create-workflow-roadmap
Generate a project workflow roadmap (docs/WORKFLOW.md) mapping plan phases to pn-core commands with model tier recommendations and per-step token cost estimates. Runs after pn-writing-plans.
pn-program-orchestration
Conductor for featureprogram: split ≥2 vertical slices, DAG, merge queue. Use when the user asks for parallel slices or /pn-program — not for a single-slice feature.
pn-github-vertical-slices
Break a plan or PRD into tracer-bullet vertical slices and create GitHub Issues via GitHub MCP (official github/github-mcp-server). Dependencies first (AFK/HITL). Use after pn-writing-plans or pn-create-prd when work must ship as Issues.
pn-paperclip
Interact with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research…
pn-feedback-analysis
Collect, analyze, and synthesize user feedback into actionable product insights. Themes, prioritization, voice of customer.
decision-logger
Capture decision traces — the reasoning behind key PM decisions. Use after PRD approvals, scope changes, launch/kill calls, prioritization shifts, or any significant product decision.