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-outline-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-outline-plan)<a href="https://agentmods.dev/skills/nirecom/agents/make-outline-plan"><img src="https://agentmods.dev/badge/skills/nirecom/agents/make-outline-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-outline-plan"><img src="https://agentmods.dev/badge/skills/nirecom/agents/make-outline-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 | $0.00048 | $0.04152 |
| Opus 5.5 | $0.00019 | $0.01661 |
| Sonnet 5.5 | $0.00010 | $0.00830 |
| Haiku 4.5 | $0.00005 | $0.00415 |
Grade A, and why
make-outline-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Propose high-level approaches and get user sign-off before detailed planning.
Skip this stage via <<WORKFLOW_OUTLINE_NOT_NEEDED: {reason}>> when a single obvious approach exists. To skip both this stage AND detail, emit WORKFLOW_OUTLINE_NOT_NEEDED and WORKFLOW_DETAIL_NOT_NEEDED in sequence.
When outline-planner returns SINGLE_APPROACH_JUSTIFIED, skip the review/sign-off loop and proceed directly to make-detail-plan.
Inputs
<INTENT_MD>— output ofclarify-intent(cross-session carry-in allowed)<PLANS_DIR>/<session-id>-survey-{code,history}.md— optional; contain## Verified Claims- All sentinels in MOP-0 are emitted by the orchestrator (Bash tool), never by a subagent.
- Session-id used for
*-outline.mdmatches the intent file actually used.
Procedure
Apply skills/_shared/resolve-plans-dir.md once; substitute the resolved absolute path for every <PLANS_DIR> below. Reuse across steps.
Run node "$AGENTS_MAIN_ROOT/bin/plan-artifact-path" --stage intent once; substitute its output for every <INTENT_MD> / $INTENT_MD below.
MOP-0. Surface premise contradictions from Research artifacts.
MOP-0a. Determine session-id from CLAUDE_CODE_SESSION_ID env (MOP-1 has not run yet — this lookup precedes intent-file resolution).
- state.steps.research.status === "skipped" → skip to MOP-0d.
- One/both <session-id>-survey-{code,history}.md missing AND research not skipped → warn once in chat ("Research artifacts incomplete — proceeding without full premise verification") and continue to MOP-0d. Do not block.
MOP-0b. Read ## Verified Claims from each existing artifact; collect items with verdict: contradicted.
MOP-0c. Any contradicted claims → display the contradicted claim list in chat; instruct the user: "The survey has found premise contradictions. Revise intent.md to reflect the correct premises and re-run /clarify-intent."; abort the skill (do not proceed further).
MOP-0d. Emit <<WORKFLOW_MARK_STEP_research_complete>> to mark Research complete (aggregating survey-code and survey-history, which no longer emit it individually; deep-research's emit, if any, is idempotent).
What ships with it
1 file 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 · +1 lines 5b246afcbcd2
- 2d ago Changed a0b1ab82b242
- 4d ago Changed 5214725c8598
- 7d ago Changed d667bac14a5c
- 9d ago Changed · +2 lines 148027d1ccb7
- 11d ago Changed ba14ba868360
- 16d ago Changed d35428dcd6b2
- 17d ago Changed · +1 lines d7b2faca09b3
- 21d ago Changed · +5 lines 2b5f84e20e52
- 29d ago First seen · 152 lines · 48 tokens per session scan A 8ada0144f12e
make-outline-plan is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 4,152 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…