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/outlinedriven/outline-driven-development/articulatenpx skills add OutlineDriven/outline-driven-development --skill articulategit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/articulate)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/articulate"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/articulate.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00609 |
| Opus 5 | $0.00034 | $0.00304 |
| Sonnet 5 | $0.00014 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
articulate 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Articulate
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user has an intended thought but cannot yet express it completely or clearly. |
| Authority | Read-only. Use only supplied material and confirmed conversation context. |
| Side effect | Chat output by default. Replace a supplied draft only when the user explicitly asks for an edit. |
| Done | The statement is audience-ready, every sentence is supported, the user's scope and identity are unchanged, and unresolved forks remain visible. |
Inputs
- The thought, fragment, notes, or draft to express.
- The intended audience and medium when already known.
- Confirmed context from the current conversation.
Procedure
- State the thought's invariant core in one sentence. Done when: the invariant core is one sentence.
- Collect only context already confirmed by the user. Do not research merely to fill a blank. Done when: only confirmed context is collected.
- Mark unsupported choices as a blank, a short alternative set, or the minimum clarifying question needed to continue. Done when: every unsupported choice is marked as a blank, alternative set, or clarifying question.
- Write the smallest complete audience-ready form that preserves the original scope, identity, confidence, and intent. Done when: the form preserves original scope, identity, confidence, and intent.
- Compare every sentence with the supplied material. Remove invented goals, requirements, rationale, facts, or certainty. Done when: no invented goals, rationale, facts, or certainty remains.
Failure and recovery
- No invariant core can be stated: the thought is too fragmentary to articulate. Ask the user for one more sentence of context; do not invent the core.
- Invented goal or fact detected: remove it and mark the gap as a blank. Do not substitute a plausible-sounding rationale.
- Scope drifted during expression: restate the original scope, discard the drift, and recheck every sentence against the supplied material.
- Unsupported choice hidden as certainty: downgrade to an explicit blank or alternative set. Do not present an unsupported choice as settled.
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.
- 2d ago First seen · 49 lines · 69 tokens per session scan A cd3e74552307
articulate is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 609 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fin-brief-generator
根据用户输入或已有研究输出（文献综述/想法报告/新颖性报告），自动生成或更新FINBRIEF.md，减少用户填写负担。.
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
deps-upgrade
Use when dependency upgrades need tiered batches for CVEs, a major release, forced compatibility, scheduled hygiene, a pre-release lockfile audit, or a cadence-driven or vulnerability-triggered sweep. Classifies each update on a risk ladder, verifies it, or defers it with a reason. Not for PR queue triage; use…
strict-validation-setup
Use when a user invokes a strict-mode validation or verifiable-goals loop setup. Bootstraps strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify. Don't use for remote, credential, publish, deploy, or irreversible changes.