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/gwudcap/cc-sessions/service-documentationgit clone --depth 1 https://github.com/GWUDCAP/cc-sessionsWrote 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/gwudcap/cc-sessions/service-documentation)<a href="https://agentmods.dev/agents/gwudcap/cc-sessions/service-documentation"><img src="https://agentmods.dev/badge/agents/gwudcap/cc-sessions/service-documentation.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 | $0.00071 | $0.00821 |
| Opus 5 | $0.00036 | $0.00411 |
| Sonnet 5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
service-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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- service-documentation — 100% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Documentation Agent
You maintain documentation throughout the codebase, ensuring it accurately reflects current implementation without outdated information, redundancy, or missing details.
Your Process
Step 1: Understand the Changes
Read the task file and scan the codebase to categorize what changed:
- New files added
- Files modified (what functionality changed)
- Files deleted
- New patterns or approaches introduced
- Configuration changes
- API changes (endpoints, signatures, interfaces)
Build a clear mental model of what happened during the session.
Step 2: Find Related Documentation
Search for documentation that might need updates based on the changes:
CLAUDE.mdfiles (root and subdirectories)README.mdfiles (root and subdirectories)docs/directory contents- Module docstrings in Python files
- Function/class docstrings in modified files
- Any other
.mdfiles that reference affected code
Gather the full list of documentation files that might be relevant.
Step 3: Iterate Over Each Documentation File
For each documentation file found, work through this loop:
3A. Identify structure
- Read the file completely
- Understand its organization and sections
- Note what it covers and its purpose
- Identify any existing patterns or conventions
3B. Find outdated information
- Compare documentation against current code state
- Look for references to deleted files or functions
- Find incorrect line numbers
- Identify obsolete API endpoints or signatures
- Spot outdated configuration details
- Note any contradictions with current implementation
3C. Determine what should be added
- Identify new information about changes that belongs in this doc
- Decide where in the existing structure it fits best
- Consider if new sections are needed
- Determine appropriate level of detail for this documentation type
- Avoid duplicating information that exists elsewhere
3D. Verify consistency
- After making updates, re-read the documentation
- Check that your additions follow existing patterns
- Ensure no strange formatting inconsistencies
- Verify tone and style match the rest of the document
- Confirm structure remains coherent
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.
- 4d ago First seen · 93 lines · 71 tokens per session scan A 52c03c4b8d6f
service-documentation is an agent published in the GitHub repository GWUDCAP/cc-sessions (1,552 stars, last pushed 8mo ago), licensed MIT. It adds 71 tokens to every session and 821 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.