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 nirecom/agents --skill make-detail-plangit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/make-detail-plan)<a href="https://agentmods.dev/skills/nirecom/agents/make-detail-plan"><img src="https://agentmods.dev/badge/skills/nirecom/agents/make-detail-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/nirecom/agents/make-detail-plan"><img src="https://agentmods.dev/badge/skills/nirecom/agents/make-detail-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 | $0.00057 | $0.03337 |
| Opus 5.5 | $0.00023 | $0.01335 |
| Sonnet 5.5 | $0.00011 | $0.00667 |
| Haiku 4.5 | $0.00006 | $0.00334 |
Grade A, and why
make-detail-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce a detailed implementation plan via a planner/reviewer discussion loop. Read intent.md + outline.md before drafting.
Procedure
When a hook blocks a sanctioned command, a fallback path is taken, or any unexpected outcome occurs, report via /supervisor-report (trigger conditions: rules/supervisor-reporting.md).
MDP-1 — Resolve <PLANS_DIR> + read artifacts
Apply skills/_shared/resolve-plans-dir.md once; substitute the resolved absolute path for every <PLANS_DIR> below. Set <INTENT_MD> / <OUTLINE_MD> to the output of node "$AGENTS_MAIN_ROOT/bin/plan-artifact-path" --stage intent / --stage outline (a resumed session reads its upstream's files); substitute them for every $INTENT_MD / $OUTLINE_MD below. Read both if present; otherwise proceed with task context alone.
MDP-2 — Surface delivery plan
Run bash "$AGENTS_MAIN_ROOT/skills/make-detail-plan/scripts/surface-delivery-plan.sh" against outline.md.
MDP-3 — Choose planner model
Run bash -c 'node "$AGENTS_MAIN_ROOT/bin/workflow/read-complexity-evaluation" --session "$SESSION_ID" --stage detail'. If line 1 is not NONE, use its model=<alias> and signals=<csv-or-none> lines directly.
If NONE (fail-open for sessions without persisted evaluation): follow skills/_shared/jev-two-stage-judge.md with point=complexity-judge stage=detail; use its model= and SIGNALS_CSV — never judge the level inline.
Emit (Claude text, not Bash): Model selected: **<model= alias>** (signals: [ids from the signals= line, or "none"]).
MDP-4 — Initial draft
Delegate to planner (Agent tool, subagent_type: detail-planner, model: <model= from MDP-3>). Pass task context + intent/outline contents.
Every detail-planner prompt carries the canonical line of the rules/shell-commands.md Subagent Dispatch Prompts section.
Every detail-planner launch — here, the MDP-5 CONTINUE re-delegate, the MDP-7 revise and re-prompt, and the research re-prompt — passes the same model: <model= from MDP-3>.
Note: the Stop-guard silence during dispatch is automatic (PostToolUse marks the step in_progress). Do not emit NEXT_STEP_PAUSE.
What ships with it
5 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.
- today Changed cbfbe8003eef
- 2d ago Changed 90584d4ce2ce
- 4d ago Changed 957a582fcc41
- 7d ago Changed 03de4b14521d
- 9d ago Changed · +2 lines 539e77f4b304
- 11d ago Changed ff93959c6a78
- 16d ago Changed 1c4f709062e2
- 17d ago Changed · +4 lines 601248b1d620
- 21d ago Changed · +2 lines f1a4224c4101
- 29d ago First seen · 122 lines · 57 tokens per session scan A 36e8d01fc493
make-detail-plan is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 3,337 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…