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/transluceai/claude-code-plugins/docentnpx skills add TransluceAI/claude-code-plugins --skill docentgit clone --depth 1 https://github.com/TransluceAI/claude-code-pluginsWhat 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 | $0.00026 | $0.00604 |
| Opus 5 | $0.00013 | $0.00302 |
| Sonnet 5 | $0.00005 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
docent 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docent
First-use notice
Before doing anything else, run:
uv tool run --quiet --from 'docent-python>=0.1.83' python -m docent.plugin.logging_config first-run-notice
If it prints a notice, relay it to the user exactly as instructed and then continue. If it prints nothing, continue silently.
Guides
This is the root skill for all Docent work. This file is just a table of contents. In most cases you should read one of the guides below before starting to work with docent. Choose the guide that best matches your task.
- For exploring a collection of agent runs, analyzing data, answering questions about agent behavior:
./analysis.md - For ingestion workflows that convert local logs or eval traces into Docent data:
./ingestion.md - If the user is asking to manipulate data in the platform through code or the command line, see the SDK reference.
Other available documentation
- For analysis-plan markdown notes (universal framework + pattern index):
./readings-reference.md(client.plan_markdown) - For writing or revising rubrics, classifier prompts, and their output schemas:
./rubric-writing.md - For plan-pattern pipelines and note templates (read one after classifying at Step 2b):
./patterns/ - For the Readings API (
client.read,client.query, batching, prompts, clustering):./readings-reference.md - For DQL syntax, schemas, quirks, and example queries:
./dql-reference.md - For the reports API:
./report.md(only if the user explicitly asks for a report) - For ingestion-side data-model and conversion examples:
./ingestion-reference.md - SDK reference is available by visiting our online documentation
Opening Docent pages
Get the user in front of the relevant Docent page as soon as it exists — a new collection or a freshly submitted analysis plan.
- In local sessions running on the user's machine (e.g. Claude Code CLI or an IDE extension), the SDK's
flush()/webbrowser.open()opens the user's default browser automatically. You can rely on this, but still surface the URL as a clickable link since the user may not notice the tab. - In sandboxed sessions where
webbrowser.open()cannot reach the user's browser (e.g. Codex CLI), surface the URL as a clickable link instead.
What ships with it
7 files 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.
- 2d ago First seen · 48 lines · 26 tokens per session scan A c1af9f21b9ed
docent is a skill published in the GitHub repository TransluceAI/claude-code-plugins (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 26 tokens to every session and 604 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…