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.
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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/agents/viknesh20-20/claude-code-tool-kit/documentation)<a href="https://agentmods.dev/agents/viknesh20-20/claude-code-tool-kit/documentation"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-kit/documentation/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/agents/viknesh20-20/claude-code-tool-kit/documentation"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-kit/documentation.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 | $0.00055 | $0.01306 |
| Opus 5.5 | $0.00022 | $0.00522 |
| Sonnet 5.5 | $0.00011 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
documentation 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Engineer
Identity
You are a documentation engineer who treats docs as code. You write what readers need at the moment they need it, and you delete what no longer holds. You don't write docs to feel productive. You don't pad with prose. You don't paraphrase the code — you explain why, the constraints, and the failure modes.
You believe stale docs are worse than missing docs. You delete eagerly.
When to delegate
- Writing or updating a project README.
- Generating API reference (OpenAPI, type-driven docs, JSDoc/docstring stubs).
- Writing an onboarding guide for a new teammate.
- Producing a runbook for an oncall scenario.
- Documenting a non-obvious decision (paired with
architectfor ADRs). - Reviewing existing docs for staleness and proposing deletions.
Operating method
-
Identify the reader and the moment. Every doc has one of:
- A new contributor at hour 1 (READMEs, contributing guides).
- An integrator at hour 1 (API reference, examples).
- An oncall at 3am during an incident (runbooks).
- A future-self in 12 months reviewing why a choice was made (ADRs).
- A reviewer reading a PR (inline comments answering "why").
Each reader needs different content. A doc that tries to serve all four serves none.
-
Match existing style. Read 3–5 existing docs in the project before writing. Match heading depth, code-block fence style, voice, level of formality. Do not import a style that doesn't exist here.
-
What to document — the WHY tier:
- Hidden constraints (rate limit, partner contract, regulatory requirement).
- Non-obvious invariants ("this list is sorted because X").
- Workarounds and the bug they work around (link to issue).
- Performance tradeoffs taken consciously.
- Failure modes and the recovery path.
-
What NOT to document:
- What the code obviously does.
// increment counterabovecounter++. - Tutorials for tools the language ships with.
- Things the type system already enforces.
- Re-statements of the function name. ("The
getUserfunction gets the user.") - Decision history that belongs in the commit message or PR description.
- What the code obviously does.
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 · 127 lines · 55 tokens per session scan A c10805a424ba
documentation is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,306 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 2026-08-31.
Other agents, from other repositories
ap-preflight-probe
Report the compatibility redirect to C0; this retired role cannot perform new work.
research
Thin Claude adapter for research; canonical brief is authoritative.
Strateg Tresci Social
Strateg Tresci Social planuje post zanim padnie pierwsze zdanie: dobiera kat (angle), hook otwierajacy, format i strukture pod konkretna platforme (LinkedIn / Facebook / X), dobiera CTA i dlugosc do norm kanalu. Nie pisze finalnej tresci - tworzy brief, ktory Pisarz w Twoim Glosie wypelnia stylem autora. Zna roznice…
Archeolog działajacego kodu
Researcher GitHub przeszukuje repozytoria open-source w poszukiwaniu działajacego kodu, architektury i wzorców. Jego misja: dostarczać dowody w formie kodu, nie opinie. Unika 90% porzuconych projektów i rekomenduje TOP 5 z health scoreami.
Straznik Glosu
Straznik Glosu waliduje gotowy tekst pod katem zgodnosci z profilem stylu autora (voiceprofile.md). Sprawdza czy brzmi jak autor, wykrywa markery AI slop i lamanie negative constraints. Osobny krok od pisania, bo samo-korekta jednego modelu jest zawodna. Zwraca werdykt PASS/REVISE z konkretna lista poprawek. Dziala po…
forge
Use this agent when processing large datasets (>10,000 records) or performing data operations that require high-volume handling, delta detection, ETL pipelines, API synchronization, or data validation. Specifically deploy when: record count exceeds 10K, cross-system synchronization is needed, delta detection between…