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/fancyboi999/open-tag/doc-syncnpx skills add fancyboi999/open-tag --skill doc-syncgit 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.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 | $0.01733 |
| Opus 5 | $0.00030 | $0.00866 |
| Sonnet 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 5d 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.
- 5d 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 (182 stars, last pushed 13d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,733 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 2026-08-30.
Other skills, from other repositories
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
skill-sublation
技能扬弃 Sublation V5.0 完整版。把执行经验沉淀为观测、候选、验证、多 Agent 协作面板、默认关闭的受控唤醒意图、Skill 分类与 shadow 精准建议、用户批准、晋升和观察窗的可审计治理链路；仅在用户明确说出 sublation 或扬弃技能时触发。.
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.
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…