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 implement-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/implement-plan)<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/implement-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/implement-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/implement-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/implement-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 | $0.00050 | $0.02505 |
| Opus 5.5 | $0.00020 | $0.01002 |
| Sonnet 5.5 | $0.00010 | $0.00501 |
| Haiku 4.5 | $0.00005 | $0.00250 |
Grade A, and why
implement-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 14d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan
You are the orchestrator. Subagents write code; you own verification, git, and the plan file.
Input: $ARGUMENTS
Reads: the plan, its spec, docs/quirks.md, git history.
Writes: code (through subagents), [T<N>] commits, the plan's state
lines, and new spec decisions the user approves.
Invariants
- The plan folder (
<root>/docs/plans/<plan>/,<root>the main checkout) is never committed, copied, or moved — one live copy, read by absolute path. - Every subagent is a fresh Agent-tool subagent given only paths and its task — never a fork of this conversation, which would carry its context in.
- The plan file is the state: checkboxes,
> Gate:,> Drift:,## Review,## Blockers,## E2E. After a context compaction, re-read the plan and spec; resume from them, never from memory. - Only you commit, tick checkboxes, and write the plan and spec. Subagents edit and test.
- Tick a task only after you re-ran its gate yourself. A subagent's "done" is a claim, not evidence.
- Commit explicit paths with
[T<N>]in the message. Nevergit add ./-A— it sweeps in unrelated files such as a copied.env. - Never weaken a gate or flip an assertion to go green.
- Run to the end. Stop for the user only on a blocker, behaviour the spec does
not decide, drift that changes a decision, contract, or later task, a
blockverdict, or an action others can see (push, PR, deploy). Ask throughAskUserQuestionwith a recommended option. Don't end a turn announcing a next step you could take.
1. Load
<root> is the main checkout:
root="$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")".
The input names a plan or a path → $root/docs/plans/<plan>/plan.md or that
path. No input → the plan prepared or implemented earlier in this session,
else the current branch name or its ticket key, else ask once. Read the plan
and its spec.
The spec's **Status:** is not plan-approved, or ## Open questions is not
empty → stop and say the plan is not ready. Raise gaps or concerns before
touching code.
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.
- 14d ago First seen · 189 lines · 50 tokens per session scan A a890936adc13
implement-plan is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 2,505 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 2026-10-03.
Other skills, from other repositories
code-commit
Commit code changes with well-structured messages following Conventional Commits. Use when ready to commit after implementation or bug fix.
ship
Inspect, split into logical commits, validate, then deliver via scripts/ship.ps1 (direct push to main, or branch + PR when main requires it).
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.
git-onboarding-auto
A Git setup and pull-request workflow automation skill. Git is the version-control tool developers use to track code changes, while a pull request is a request for teammates to review and merge those changes.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple…
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.