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/conectlens/lenserfight/docs-managernpx skills add conectlens/lenserfight --skill docs-managergit clone --depth 1 https://github.com/conectlens/lenserfightWrote 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/conectlens/lenserfight/docs-manager)<a href="https://agentmods.dev/skills/conectlens/lenserfight/docs-manager"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/docs-manager.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 | $0.00072 | $0.00690 |
| Opus 5 | $0.00036 | $0.00345 |
| Sonnet 5 | $0.00014 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
docs-manager 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-manager
Helps with documentation work in this repo.
Sources of truth
| What to verify | Where to look |
|---|---|
| Feature behavior | libs/domains/* |
| Platform rules | libs/platform/* |
| DB schema / RLS | supabase/migrations/* |
| CLI commands & flags | apps/cli/src/commands/* |
| Existing doc content | docs/en/** (default) · other active locales (e.g. docs/tr/**) |
| Sidebar config | apps/docs/.vitepress/config.ts |
Diátaxis quick guide
| Type | Folder | For |
|---|---|---|
| tutorial | tutorials/ |
Learning by doing |
| how-to | how-to/ |
Reaching a goal |
| reference | reference/ |
Looking things up |
| explanation | explanation/ |
Understanding concepts |
When unsure: how-to if the reader does something; reference if they look up something.
Language flow (GRASP — Information Expert + Pure Fabrication)
/en/ is the default and the Information Expert for documentation content — the canonical source other locales are derived from. Write or update English first, then adapt to each other active locale (e.g. /tr/) as a downstream port. This keeps a single authoritative origin and prevents conflicting edits across languages (low coupling, high cohesion).
- Always create/update the
docs/en/**page first. - After EN is correct, adapt to each other active locale present under
docs/<lang>/**. - If a locale's page doesn't exist yet, mirror the structure and mark untranslated prose with
<!-- TODO: translate -->.
SEO & GEO
Write pages so both search engines and generative-AI answer engines can surface them: meaningful title/description frontmatter, clear H1, semantic headings, plain factual phrasing, and unambiguous entity names (product, command, API).
Suggested flow
- Find the gap — grep
docs/en/(and other active locale folders), check the sidebar. - Compare doc against the source of truth listed above.
- Update only what drifted. Keep the existing voice.
- Write/update EN first, then adapt to other active locales.
- Update
apps/docs/.vitepress/config.tsif a page was added or moved. - Run
pnpm nx build docsand fix broken links.
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.
- 5d ago First seen · 59 lines · 72 tokens per session scan A aaa9a7a2ecf8
docs-manager is a skill published in the GitHub repository conectlens/lenserfight (19 stars, last pushed 25d ago), licensed MIT. It adds 72 tokens to every session and 690 once invoked, about $0.0004 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
evaluate-pattern-adoption
Run or plan this repository's pattern-adoption evidence evaluation locally with signed-in Codex agents. Use when asked to refresh stale evidence, assess stable or exploratory patterns, evaluate one or all catalog patterns, discover possible new patterns, or prepare a reviewable evidence PR without model-backed GitHub…
contributing-to-awesome-claude
Use when writing, testing, or preparing ANY contribution or pull request to the JSONbored/awesome-claude (HeyClaude) repo — adding a community content entry (agent/MCP server/skill/hook/command/rule/guide/collection/statusline), or making a platform/code change (website, registry package, MCP package, scripts). The…
contributor-pipeline-gardening
Maintenance of the contributor issue pipeline for JSONbored/awesome-claude (HeyClaude) — closing issues that are already done but not marked so, and keeping a small, high-value contributor-available backlog stocked with real website/content/feature/bugfix work. Runs every 24h via a dedicated scheduled task. Invoke for…
skills
本目录保存按需阅读的项目参考文档。根目录 CLAUDE.md 负责最小项目上下文与硬性约定；本文档用于选择更详细的专题文档。.
rails-audit-skill
Perform comprehensive technical reviews of Ruby on Rails applications. Runs automated analysis tools (RubyCritic, Brakeman, bundler-audit, Gitleaks, Debride, linters, SimpleCov, Rails stats, Rails ERD), analyzes code for architecture, security, authorization (Pundit/CanCanCan), dead code, and design issues, and…
caching-strategies
When improving read performance and reducing database load.