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/pxsloot/gitea-mcp-server/docsnpx skills add pxsloot/gitea-mcp-server --skill docsgit clone --depth 1 https://github.com/pxsloot/gitea-mcp-serverWrote 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/skills/pxsloot/gitea-mcp-server/docs)<a href="https://agentmods.dev/skills/pxsloot/gitea-mcp-server/docs"><img src="https://agentmods.dev/badge/skills/pxsloot/gitea-mcp-server/docs.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 | $0.01136 |
| Opus 5 | $0.00000 | $0.00568 |
| Sonnet 5 | $0.00000 | $0.00227 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
docs 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Handbook
This is the project knowledge base. It covers the conventions, workflows, and principles you need to work on gitea-mcp-server. Everything here is available directly — no skill loading required.
Documentation map: See
docs/INDEX.mdfor the full doc set with audience, type, and topic ownership for every document.
Documentation philosophy
Code, comments, docstrings, tests, and the docs/ directory together form a
single layered knowledge base. Through an index (docs/INDEX.md) this
knowledge is navigable, making discovery straightforward.
- Documentation is as much a deliverable as code.
- A doc that says where to look is more valuable than one trying to say everything.
- Always update and improve the documentation. It makes the next job easier.
The structural policies that follow from this philosophy (audience split,
de-duplication invariant, pragmatic Diátaxis) live in
docs/DOCUMENTATION_STANDARDS.md.
RED FLAGS — STOP AND ABORT
- ✗ Starting work without reading the relevant
docs/INDEX.mdfirst to navigate the docs - ✗ Editing files on
mainbranch - ✗ PR without
Fixes #XXreference - ✗ "Quick fix" that skips issue creation
- ✗ Ignoring test failures
- ✗ Launching a discovery for things already documented
- ✗ Launching a subagent for static code structure discovery (the docs already have module maps, pipeline diagrams, and data flows)
Any of these means: Abort. Create issue, create proper branch, read relevant doc, follow full workflow.
Verification Checklist (before PR)
- Branch created from latest
main - Branch name follows
type/XX-descriptionformat - All changes on branch, not main
- Documentation, meta docs, docstrings, comments, instructions up to date. This check is NOT optional. Remember: you are intended audience of the documentation.
- No debug/console.log statements
- Tests pass (
make test) - PR body includes
Fixes #XX - Self-review completed
What ships with it
19 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.
- AGENT_INSTRUCTIONS_STANDARDS.md 6.5 KB
- ARCHITECTURE.md 68 KB
- DEVELOPMENT.md 57 KB
- DOCUMENTATION_STANDARDS.md 7.2 KB
- INDEX.md 5.1 KB
- SCOPE_MODEL.md 10 KB
- TESTING_STANDARDS.md 5.2 KB
- testing/ASSERTIONS.md 1.8 KB
- testing/CI.md 1.4 KB
- testing/CONTEXTVAR.md 2.5 KB
- testing/FIXTURES.md 5.1 KB
- testing/INTEGRATION.md 3.5 KB
- testing/LAYOUT.md 8.6 KB
- testing/LINTING.md 5.6 KB
- testing/LIVE.md 21 KB
- testing/MOCKING.md 4.5 KB
- testing/PATTERNS.md 10 KB
- testing/ZONES.md 5.0 KB
- TOOL_ANNOTATIONS.md 7.7 KB
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 · 143 lines · 0 tokens per session scan A 4313bc38e179
docs is a skill published in the GitHub repository pxsloot/gitea-mcp-server (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,136 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 skills, from other repositories
c-03-repo-bootstrap
Bootstrap onboarding for undocumented repos or existing memory slices. Builds root overviews, route-local overview pillars, evidence packs, file cards, onboarding waves, deleted-slice cleanup, curator reviews, and handoff while keeping the orchestrator thin.
c-12-closeout
Close out approved Agents Remember edits by preserving approval authority, mandatory strict code quality before code commit, missing-onboarding checks, external-memory refresh, memory quality, ledger alignment, and no automatic push.
c-02-memory-quality-control
Control Agents Remember memory quality with task-start drift checks, pre-code-commit missing-onboarding checks, and closeout memory quality gates.
c-13-install-and-onboard
After the harness starter package and MCP server are wired and the harness has restarted, run/verify runtimeinstall, set up the memory repo, bootstrap onboarding when scaffolding new, and configure providers to index the code and memory.
c-00-initialize-memory-repo
Initialize or repair the Agents Remember memory root for a target repository. Defaults to repo-local internal memory; creates an external memory repo only when the developer explicitly asks for external memory.
c-04-retrieval-strategy-router
Choose retrieval strategies across memory substrates: semantics for known concepts with unknown structure, relationships for known anchors with unknown connections, and intent for hidden contracts and code truths.