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/dnlbox/ai-protocol/plan-implementationnpx skills add dnlbox/ai-protocol --skill plan-implementationgit clone --depth 1 https://github.com/dnlbox/ai-protocolWhat 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 | $0.00016 | $0.00838 |
| Opus 5 | $0.00008 | $0.00419 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
plan-implementation 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan implementation
Use this skill when the user explicitly requests operational planning or re-planning.
Do not invoke this skill merely because implementation needs a lightweight internal plan.
Start
- Read every file in
docs/concept/. - Inspect the existing implementation.
- Inspect the existing execution contract.
- Inspect the latest verified state.
- Require accepted concept intent.
- Identify unresolved product decisions.
- Return unresolved product decisions to the user.
- Resolve reversible technical choices during planning.
- Preserve accepted implementation evidence during re-planning.
- Preserve completed history during re-planning.
- Change only the approved planning scope.
Plan by objective
- Define objectives as observable product outcomes.
- Prefer a complete vertical feature over technical-layer phases.
- Include every required product layer in the objective.
- Include the natural-entry playtest path in an interaction objective.
- Define the completion condition for each objective.
- Define the required validation boundary for each objective.
- Record material dependencies between objectives.
- Avoid prescribing the number of agents.
- Avoid prescribing the execution order when dependencies do not require one.
- Avoid creating implementation packets for minor mechanical steps.
- Let the Leader decompose an approved objective during execution.
Execution contract
- Keep Project Specifics limited to stable repository rules.
- Record exact supported commands in Project Specifics.
- Record required validation gates in Project Specifics.
- Record material architecture boundaries in Project Specifics.
- Record material security boundaries in Project Specifics.
- Record material external-operation gates in Project Specifics.
- Avoid copying product intent into Project Specifics.
- Avoid copying the execution plan into Project Specifics.
State
- Create
BUILD_STATE.mdwhen implementation needs durable continuity. - Keep
BUILD_STATE.mdfocused on current verified truth. - Record one current objective in
BUILD_STATE.md. - Record one next meaningful action in
BUILD_STATE.md. - Record active ownership in
BUILD_STATE.md. - Record material decisions in
BUILD_STATE.md. - Keep completed detail in git history.
- Avoid turning
BUILD_STATE.mdinto a task transcript.
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 · 106 lines · 16 tokens per session scan A 82b71a37566c
plan-implementation is a skill published in the GitHub repository dnlbox/ai-protocol (18 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 838 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 2026-08-30.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…