Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/docs-outbox/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/docs-outbox)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/docs-outbox"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/docs-outbox/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/smart-ai-memory/attune-ai/docs-outbox"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/docs-outbox.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 | $0.00067 | $0.00697 |
| Opus 5.5 | $0.00027 | $0.00279 |
| Sonnet 5.5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
docs-outbox 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 1mo 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.
Docs Outbox
IMPORTANT: Start your response by telling the user: you are running the docs-outbox sweep — it composes a digest for approval and never ships anything on its own.
What It Does
Small docs artifacts (lessons, roundtable reports, process drafts,
plans) land as per-artifact timestamped files in
~/.attune/docs-outbox/ instead of shipping as their own PRs.
This skill runs the curating sweep: dedupe, lint, core-worthy
flagging, ONE digest — then the chair approves via chip before a
single batched PR opens. decisions.md rulings and spec status
flips NEVER route here; they merge now (R2).
Invariants:
- No auto-shipping — the chair (or their chip-spawned session) approves the digest before any PR opens (R4).
- One swept PR per approval, auto-merge, containing every clean artifact in timestamp order.
- Artifacts with lint issues stay in the outbox untouched.
Step 1 — status
Version preflight first: if python -m attune.docs_outbox status
fails with "No module named attune.docs_outbox", the installed
attune-ai wheel predates this module — upgrade it
(pip install --upgrade attune-ai) before continuing rather than
working around it with PYTHONPATH.
Run python -m attune.docs_outbox status. If the outbox is empty,
say so and stop. If the status line says STALE (oldest 2+ days),
surface the warning prominently.
Step 2 — sweep
Run python -m attune.docs_outbox sweep from the repo root and
show the digest to the user verbatim (it is one screen: pending
count, per-artifact table with core-worthy / related-slug / lint
flags, dropped exact duplicates).
Step 3 — chip approval
Present the digest as a chip via the spawn_task tool:
- title:
Approve docs-outbox digest (N docs) - tldr: one sentence — how many docs, oldest age, any flags.
- prompt: the digest text, plus instructions for the spawned
session: create a branch off origin/main, run
python -m attune.docs_outbox apply --repo-root ., review the diff, commit (docs(outbox): sweep N artifacts), push, open ONE auto-merge PR, and report skipped artifacts.
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.
- 1mo ago First seen · 69 lines · 67 tokens per session scan A a908bce254bb
docs-outbox is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 697 once invoked, about $0.0003 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
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
working-in-turns
Keep each turn bounded, checkpointed, and reviewable.
gear
Managing dependencies, CI/CD, advanced GitHub Actions workflows, containers, secrets, and operational config. Use for build, workflow, or environment work.
launch
Planning releases and reporting delivery work from GitHub PR history. Use when versioning, CHANGELOGs, rollout or rollback plans, engineering metrics, retrospectives, or stakeholder reports are needed.
worktree
Isolate parallel work in a git worktree of the current repository (worktree tool: status / new / merge / remove). Use when another live session is dirty in the same directory (listagents), when two agents would fight over index.lock, or when starting a parallel task checkout.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.