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 agents/viknesh20-20/claude-code-tool-kit/documentationgit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWhat 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 | $0.00055 | $0.01306 |
| Opus 5 | $0.00028 | $0.00653 |
| Sonnet 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 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 — 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.
- 2d 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 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,306 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 2026-08-31.
Other agents, from other repositories
bird
"Is this correct?" — Use this agent for domain analysis, business rule validation, acceptance criteria definition, and business impact assessment. Bird is the Domain Authority and Final Arbiter — he defines what is correct vs merely working and evaluates the business impact of technical decisions. Use via /team for…
mj
"How should we build this?" — Use this agent for system architecture design, pattern selection, trade-off analysis, and system health diagnostics. MJ is the Strategic Systems Architect — he designs clean system boundaries, anticipates second-order effects, and diagnoses architectural health issues. Use via /team for…
kobe
"What could break?" — Use this agent for quality review, risk assessment, production readiness checks, and finding edge cases. Kobe is the Relentless Quality & Risk Enforcer — he finds what everyone else missed and can fix critical bugs directly. Use via /team for orchestrated workflows, or directly for standalone…
magic
"Summarize everything." — Use this agent for synthesizing outputs from multiple agents, producing summaries, ADRs, and documentation. Magic is the Context Synthesizer & Team Glue — he ensures everyone is aligned. Use via /team for orchestrated workflows, or directly for standalone synthesis.\n\n \nContext: Multiple…
pippen
"Will it stay working?" — Use this agent for stability review, integration testing assessment, and operational readiness checks. Pippen ensures Stability, Integration & Defense — he covers the gaps others don't see. Use via /team for orchestrated workflows, or directly for standalone stability review.\n\n \nContext…
shaq
"Build it." — Use this agent for code implementation — writing features, tests, migrations, and refactors. Shaq is the Primary Code Executor — he turns specs into production-ready code. Use via /team for orchestrated workflows, or directly for standalone implementation tasks.\n\n \nContext: Team has specs ready and…