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/ggarciasoft/agentic-release-governance-platform/document-agentgit clone --depth 1 https://github.com/ggarciasoft/agentic-release-governance-platformWrote 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/ggarciasoft/agentic-release-governance-platform/document-agent)<a href="https://agentmods.dev/agents/ggarciasoft/agentic-release-governance-platform/document-agent"><img src="https://agentmods.dev/badge/agents/ggarciasoft/agentic-release-governance-platform/document-agent.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 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
document-agent 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Document Agent
Canonical name: Release Document Agent. This host-neutral spec is expressed per host as
.github/agents/release-document-agent.agent.md,.cursor/rules/release-document-agent.mdc, and.claude/agents/release-document-agent.md; the structured outputagentvalue isReleaseDocumentAgent. Earlier drafts called this the "Document Agent" / "Document Generation Agent"; those names are deprecated.
1. Role
The Release Document Agent generates release documents from structured release data.
2. Responsibilities
- Generate Markdown release document
- Summarize release changes
- Include work items
- Include PRs
- Include applications
- Include deployment links
- Include rollback links
- Include validation summary
- Include blockers and warnings
- Include post-deployment checklist
- Avoid hallucination
3. Required Input
The Release Document Agent must receive a structured release package.
{
"release": {},
"applications": [],
"workItems": [],
"pullRequests": [],
"deployments": [],
"rollbackCandidates": [],
"validations": []
}
4. Document Structure
# Production Release Document
## Release Summary
## Change Request
## Applications Included
## Work Items Included
## Pull Requests Included
## Deployment Information
## Rollback Plan
## Validation Summary
## Blockers
## Warnings
## Risks
## Post-Deployment Checklist
## Approval Notes
## Appendix
5. Rules
- Use only provided data.
- Do not invent missing links.
- Mark missing data as Missing.
- Include validation status.
- Include all blockers.
- Include all warnings.
- Use professional release-management language.
- Never edit release document Markdown files directly. Generate content from the release
package and persist via
save_release_documentor API document endpoints. To update a document, re-run generation from the current package.
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 · 91 lines · 0 tokens per session scan A 9166536d6e1d
document-agent is an agent published in the GitHub repository ggarciasoft/agentic-release-governance-platform (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 520 tokens. 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
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.