Borrowing it
Nothing to install: this file belongs to fancyboi999/open-tag. 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/fancyboi999/open-tag/main/.agents/skills/doc-sync/SKILL.mdgit clone --depth 1 https://github.com/fancyboi999/open-tagWrote 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/fancyboi999/open-tag/doc-sync)<a href="https://agentmods.dev/skills/fancyboi999/open-tag/doc-sync"><img src="https://agentmods.dev/badge/skills/fancyboi999/open-tag/doc-sync/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/fancyboi999/open-tag/doc-sync"><img src="https://agentmods.dev/badge/skills/fancyboi999/open-tag/doc-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 12 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.01733 |
| Opus 5.5 | $0.00024 | $0.00693 |
| Sonnet 5.5 | $0.00012 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
doc-sync 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doc-sync — keep docs and code converged
This repo treats doc lag as an unfinished bug (see AGENTS.md § Doc-sync discipline). This skill is the executable procedure; the canonical mapping table (which change owes which doc) lives in AGENTS.md — read it there, do not copy it here.
This file is canonical at
.agents/skills/doc-sync/SKILL.md(.claude/skills/doc-syncis a symlink). The skill itself iterates: when a run shows an instruction here is wrong or misleading, fix it in the same pass, with the run's evidence in the commit message.
Mode 1 — per-change sync (run at the end of every change)
-
Determine the change surface.
git diff --stat origin/main...HEAD(or the staged diff for uncommitted work). -
Map each changed path against the AGENTS.md doc-sync table. Produce the list of docs owed by this change. The high-traffic rows:
src/db/schema.ts→docs/generated/db-schema.md(hand-maintained snapshot — no generator script exists despite thegenerated/dir name; update the table row and any enum lists by hand; prod DB migrates viaprod:up→db:push:prod).- Routes / CLI subcommands / daemon protocol →
ARCHITECTURE.md§II codemap + §IV contracts. - Module purpose / boundary / invariant changed →
ARCHITECTURE.md§II–IV. - Feature completed or modified →
FEATURES.mdcheckbox (checkbox + a short note; long verification narratives belong in the PR, not the checklist). - TODO / known drift left behind →
docs/tech-debt-tracker.mdnew entry (next free ID — check the archive too so IDs are never reused). src/daemon/**shipped in the bundle → bumppackages/daemon/package.json, cut a GitHub Release, and add the version'sCHANGELOG.mdentry. Merged ≠ shipped.
-
Status single-source rule. Security/authorization item states (F*/C*/IDOR-B*) live only in
docs/authorization.md§6. Other docs (PLANS, tech-debt I44) may point there but must never mirror per-item states — mirrored lists are how C10 stayed "remaining" for weeks after it was fixed. Detect mechanically, don't trust prose:grep -rnE '\b(C1[0-2]|C[1-9]|B[1-6]|F[0-9]|IDOR)\b' --include='*.md' docs/ *.md | grep -vE 'authorization\.md|docs/exec-plans/|docs/superpowers/'(historical plan/spec records legitimately narrate the states they shipped — the rule polices live docs). A hit naming an item's state (open/fixed/remaining) is a violation; a bare pointer to authorization.md §6 is fine.
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 · 99 lines · 0 tokens per session scan A d409fe74db81
doc-sync is a skill published in the GitHub repository fancyboi999/open-tag (213 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,733 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 2026-08-30.
Other skills, from other repositories
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
room-playbook
Lightweight default rules for coordinating a Room conversation without confusing chat wakeups with durable WorkGraph responsibility.
skill-sublation
A governed workflow for improving agent skills through observations, proposed changes, testing, review, user approval, and a period of monitoring. “Sublation” means preserving useful existing behavior while adding a verified improvement.
ad-creative
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
ai-seo
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…