Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nicograef/handbook/plugin install nicoWrote 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/nicograef/handbook/implement-plan)<a href="https://agentmods.dev/skills/nicograef/handbook/implement-plan"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/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/nicograef/handbook/implement-plan"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/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 | $0.00055 | $0.01402 |
| Opus 5.5 | $0.00022 | $0.00561 |
| Sonnet 5.5 | $0.00011 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan
Carry a plan from docs/plans/ to landed commits on the base branch, with no human turn between phases. Progress is durable only once committed and ticked.
With two or more plan paths, follow programme.md instead. Open lead.md before the first dispatch, on a stop and before landing.
Gotchas
- Invoking this skill arms a session-long Stop hook. It blocks a stop once per commit while
plan/<slug>holds an unticked criterion. Commit## Run statebefore a genuine stop. - The plan copy on the base branch is stale during the run by design. Read and tick it in the run worktree.
- Redoing finished work is the most expensive failure. Resume first, on every invocation.
- The log outranks the checkbox. A tick without a trailer commit is unticked; a trailer commit without a tick is re-verified, then ticked.
- Pass the plan to every agent as a path. Pasted phase text goes stale on the first tick.
- Pin the base once as a sha and target it in every dry run, rebase and merge.
- Only the lead writes the plan file.
Steps
- Resume. Finish or abort a half-open rebase or merge only from its owning worktree.
- Read the plan. Detect the base from
origin/HEAD, elsegit ls-remote --symref origin HEAD; ask if neither resolves. - Review the unmet phases in one pass: ambiguous or unverifiable criteria, missing files, commands the allowlist lacks.
- Phases passing the concurrency test run as parallel lanes, up to the writer cap in lead.md. Set each phase's review tier.
- State the run contract once and start: base sha, phase grouping and tiers, worktrees, verify command. Only open forks and missing allowlist commands wait for the user.
- Create
../<repo>-wt/plan/<slug>on branchplan/<slug>from the pinned base. Confirm the verify command passes on unchanged code. - Run sequential phases in the run worktree. A concurrent phase gets its own worktree, branch and agent.
- Commit per criterion with the trailer
Plan: <slug> phase <N> criterion <M>. One targeted check per criterion, reusing an existing test or gate before writing one; the full gate once per phase. - Tick a phase's criteria in one commit when it closes, only what a tool result proves. An existing test, lint, typecheck or command output counts.
- Fold each lane into
plan/<slug>in phase order: rebase onto the run tip,merge --ff-only, re-verify. - Delete
## Run statein its own commit, then land as lead.md says.git rmthe plan only when every criterion is ticked. - Report phases complete and blocked, criteria ticked, commits landed, dropped agents and the plan file's fate.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 38052cbb0842
- 12d ago Changed d964b7cfef3b
- 18d ago Changed · +11 lines ad7adc6ba1ca
- 23d ago Changed 6b6602a7eb81
- 28d ago Changed · +6 lines · +55 tokens per session b0bbf122357c
- 1mo ago Changed d6dac2c94fa8
- 1mo ago Changed · -12 lines e73ddc617ba0
- 1mo ago Changed 0848abb9843a
- 1mo ago Changed · -1 lines c0a0e1b67b95
- 1mo ago First seen · 81 lines · 0 tokens per session scan A a39f95693f89
implement-plan is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,402 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.
implement-plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| implement-plannicograef/handbook | Skill | 2 | 2d ago | MIT | A | 55 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 6d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | 2d ago | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |