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/robertguss/claude-code-toolkit/doc-refreshnpx skills add robertguss/claude-code-toolkit --skill doc-refreshgit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWhat 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 | $0.00038 | $0.00874 |
| Opus 5 | $0.00019 | $0.00437 |
| Sonnet 5 | $0.00008 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
doc-refresh 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Refresh Skill
Use this skill when asked to overhaul, refresh, modernize, or clean up a
repository's documentation — especially for a system that is already in
production and has accumulated stale README content, dead analysis docs,
outdated AI-agent knowledge bases (AGENTS.md, CLAUDE.md, etc.), or
misleading code comments.
This skill is repo-agnostic. It does not assume any particular language, framework, or doc tool. It encodes a phased process, a reusable checklist, and a set of anti-patterns learned from running this refresh on real production repos.
When to use this skill
- The user says something like "our docs are out of date," "refresh the README," "clean up AGENTS.md," "audit our documentation," or "set up a docs/ folder with architecture diagrams."
- A repo has legacy analysis files, dead feature references, or docs that no longer match the live code.
- The user wants a repeatable framework they can reuse across repos.
How to use this skill
- Read
CHECKLIST.mdin this skill directory for the phase-by-phase process (Phase 0 through Phase 6). - Read
ANTI-PATTERNS.mdfor common mistakes to avoid while auditing and rewriting docs. - Adapt the checklist to the target repo:
- Confirm with the user which phases apply (a small repo may not need every phase; a large one may want each phase in its own session to protect context windows).
- Identify the repo's actual doc tooling (Markdown + Mermaid is the default assumption below, but adjust if the repo uses something else, e.g. Sphinx, Docusaurus, or a wiki-only workflow).
- Always produce (or update) a running "roadmap" file in the repo root
(e.g.
DOCUMENTATION_ROADMAP.md) that captures the plan, audit findings, and a "Lessons Learned" scratchpad. This gives future sessions (human or agent) a clear handoff point and turns the current refresh into reusable material for the next one. - At natural session boundaries, write or update a
HANDOFF.mdsummarizing what was done, what was verified, and exactly what the next session should do next. Treat this as mandatory when the work will span more than one session. - Before declaring any phase complete, run the repo's actual lint/test
command (discover it from
AGENTS.md,README.md,justfile,package.json,Makefile, or CI config) to make sure doc-only changes didn't break anything, and re-check for stale references introduced by the phase's own edits.
What ships with it
2 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 · 76 lines · 38 tokens per session scan A 1b069c37d8a0
doc-refresh is a skill published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 24d ago), licensed MIT. It adds 38 tokens to every session and 874 once invoked, about $0.0002 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
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-edr-evasion
EDR evasion offensive checklist: hook unhooking (user/kernel), direct syscalls, PPID spoofing, process injection variants, AMSI bypass, ETW patching, memory encryption, and behavior-based evasion. Use when planning EDR bypass during red team engagements or researching AV/EDR evasion techniques.
offensive-mitigations
Security mitigation reference and bypass catalog: ASLR, DEP/NX, RELRO, stack canaries, CFI, sandboxing, seccomp. Covers both detection of enabled mitigations and known bypass techniques. Use when assessing target hardening or planning exploit mitigation bypasses.
offensive-exploit-development
Exploit development operational guide: environment setup, debugging workflow, PoC development lifecycle, writing reliable exploits, using pwntools/pwndbg, heap exploitation techniques, and weaponization considerations. Use when actively developing exploits or setting up an exploit dev environment.
offensive-tls-attacks
Comprehensive methodology for auditing and exploiting TLS/SSL implementations and misconfigurations across network services and mobile applications. Covers protocol downgrade attacks including POODLE (CVE-2014-3566) against SSLv3 CBC padding, DROWN (CVE-2016-0800) cross-protocol attack leveraging SSLv2 export ciphers…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…