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 OutlineDriven/outline-driven-development --skill doc-coauthoringgit 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/doc-coauthoring)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/doc-coauthoring"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/doc-coauthoring/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/outlinedriven/outline-driven-development/doc-coauthoring"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/doc-coauthoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.01259 |
| Opus 5 | $0.00023 | $0.00629 |
| Sonnet 5 | $0.00009 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
doc-coauthoring 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc coauthoring
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to write a doc, proposal, spec, RFC, design doc, decision doc, or PRD. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The document is drafted and iterated as chat output only. |
| Side effect | Drafts and iterates a structured document in chat; never writes, creates, or edits files. |
| Done | The document passes reader testing against a fresh-context reader and meets the user''s stated impact goals. |
Inputs
Required from the user:
- Document type (e.g., technical spec, decision doc, proposal, RFC, PRD, design doc).
- Primary audience.
- Desired impact when someone reads the document.
Optional:
- A template or specific format to follow (link, pasted text, or description).
- Constraints, timeline pressures, organizational context, related discussions, technical architecture, stakeholder concerns.
- An existing draft to edit.
The user may supply context in shorthand, as an unstructured context dump, or by pointing to material to paste. Ask clarifying questions to close gaps; never invent missing context.
Procedure
-
Offer the three-stage workflow: Context Gathering, Refinement & Structure, and Reader Testing. If the user declines, work freeform and stop this procedure. Done when: the user accepts the three-stage workflow or the skill stands down.
-
Stage 1: Context Gathering. Done when: context gaps are closed and the user clears the move to drafting.
- Ask for meta-context: document type, primary audience, desired impact, template/format, and constraints.
- If the user names a template or existing draft, ask them to share or paste it; read what is provided.
- Ask for an unstructured dump of all relevant context (background, alternatives rejected, organizational context, timeline, architecture, stakeholder concerns).
- Once the initial dump is done, ask 5-10 clarifying questions targeting gaps. The user may answer in shorthand.
- Exit Stage 1 when questions reach edge cases and trade-offs without needing basics explained. Ask whether the user wants to add more context before moving on.
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 Changed · -16 tokens per session 57a7f4b5e1e5
- 5d ago First seen · 69 lines · 63 tokens per session scan A 589572e6d839
doc-coauthoring is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,259 once invoked, about $0.0002 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
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.