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/ai-collab-protocolsnpx skills add OutlineDriven/outline-driven-development --skill ai-collab-protocolsgit 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/ai-collab-protocols)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/ai-collab-protocols"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/ai-collab-protocols.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 | $0.00060 | $0.00828 |
| Opus 5 | $0.00030 | $0.00414 |
| Sonnet 5 | $0.00012 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
ai-collab-protocols 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 yesterday.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI collab protocols
Contract
| Field | Bound contract |
|---|---|
| Trigger | User describes an AI workflow gap or uses an ambiguous cross-session reference such as 'the PR Bob mentioned' or 'that bug from last week'. |
| Authority | Read-only: reply content only; no file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | None; reply content only. |
| Done | Every ambiguous reference resolves to a stable handle; anti-patterns surface when reached. |
Inputs
The user's message may contain ambiguous references: names or descriptions without locators, such as "the PR Bob mentioned", "that bug from last week", or "the function we discussed". It may instead describe a workflow gap. When asked, the user may optionally supply a stable handle: a GitHub PR or comment permalink, an MCP resource URI such as @github:pr/owner/repo/123#comment-456, or a file:line reference. The skill fetches and mutates nothing; it asks the user for the handle.
Procedure
- Scan the user's message for ambiguous references — a name or description without a locator — or a described workflow gap. If none is present, do not route. Done when: every ambiguous reference or workflow gap is identified.
- For each ambiguous reference, stop and ask the user for a stable handle: a GitHub PR/comment permalink, an MCP resource URI (e.g.
@github:pr/owner/repo/123#comment-456), or a file:line reference. State why: names are ambiguous in long-context sessions and unrecoverable across sessions, while a stable URL survives compaction and enables exact match. Done when: each reference has a stable handle or is marked unresolved. - Surface one tactic at a time, not a lecture. When the user is handing off multi-session work, recommend leaving a comment on the PR — an addressable, compaction-surviving thread — over a chat-only handoff, so the next session, colleague, or agent can resume without replaying context. Done when: one tactic is surfaced.
- When an anti-pattern is reached, surface it: (a) screenshot-only context loses URL grounding, copy-paste, and search — pair every screenshot with its URL or text export; (b) token-usage or lines-of-code framing as a quality proxy — quantity is not capability; surface the rejection. Done when: each reached anti-pattern is named.
- Stop once every ambiguous reference has a stable handle and any reached anti-pattern has been named. Do not widen scope or invent handles the user did not supply. Done when: every reference has a handle and reached anti-patterns are named.
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.
- yesterday First seen · 38 lines · 60 tokens per session scan A eb0d05b1d53c
ai-collab-protocols is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 828 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.
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…
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.
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.