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/vasilyu1983/ai-agents-public/docs-codebasenpx skills add vasilyu1983/AI-Agents-public --skill docs-codebasegit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/docs-codebase)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/docs-codebase"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/docs-codebase.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 | $0.00036 | $0.03206 |
| Opus 5 | $0.00018 | $0.01603 |
| Sonnet 5 | $0.00007 | $0.00641 |
| Haiku 4.5 | $0.00004 | $0.00321 |
Grade A, and why
docs-codebase 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 3d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Documentation
Use this skill to write, restructure, and verify software-repo documentation: READMEs, runbooks, API references, changelogs, onboarding docs, instruction files, and canonical docs libraries for humans and coding agents.
The goal is durable docs, not document sprawl. Keep one canonical doc per subject, wire in ownership and review cadence, and verify filesystem-backed claims before publishing summary docs.
Quick Reference
| Documentation Type | Template | Notes |
|---|---|---|
| project README | assets/project-management/readme-template.md | onboarding and project navigation |
| ADR or architecture note | assets/architecture/adr-template.md | decision record |
| gap analysis or migration assessment | assets/architecture/gap-analysis-template.md | architecture and readiness work |
| API reference | assets/api-reference/api-docs-template.md | REST, GraphQL, gRPC, AsyncAPI |
| changelog | assets/project-management/changelog-template.md | release history |
| contributing guide | assets/project-management/contributing-template.md | team and OSS contribution |
| docs IA or consolidation plan | assets/docs-as-code/docs-structure-template.md | large doc sets |
| ownership and review model | assets/docs-as-code/ownership-model.md | runbooks and critical docs |
| doc sync checklist | assets/project-management/template-doc-sync-checklist.md | status and path integrity |
| operational runbook | assets/operational/runbook-template.md | SLO, alerts → response, rollback, escalation, postmortems; use {{PLACEHOLDER}} format |
| CI markdownlint config | assets/ci/.markdownlint.yaml | drop into repo root; MD013 off, MD024 siblings_only, sensible defaults |
| CI Vale prose config | assets/ci/.vale.ini | Microsoft style base; passive voice as suggestion; per-rule overrides documented |
| CI docs quality workflow | assets/ci/docs-quality.yml | GitHub Actions: markdownlint + markdown-link-check + vale on docs/ PRs |
What ships with it
34 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.
- agents/openai.yaml 328 B
- assets/api-reference/api-docs-template.md 11 KB
- assets/architecture/adr-template.md 6.2 KB
- assets/architecture/gap-analysis-template.md 1.8 KB
- assets/ci/.markdownlint.yaml 1.7 KB
- assets/ci/.vale.ini 1.9 KB
- assets/ci/docs-quality.yml 2.0 KB
- assets/docs-as-code/docs-structure-template.md 1.8 KB
- assets/docs-as-code/ownership-model.md 1.8 KB
- assets/operational/runbook-template.md 4.7 KB
- assets/project-management/changelog-template.md 6.7 KB
- assets/project-management/contributing-template.md 11 KB
- assets/project-management/readme-template.md 8.3 KB
- assets/project-management/template-doc-sync-checklist.md 920 B
- data/sources.json 18 KB
- learnings.consolidated.md 589 B
- learnings.md 465 B
- references/adr-writing-guide.md 21 KB
- references/ai-documentation-tools.md 8.5 KB
- references/api-documentation-standards.md 20 KB
- references/backlog-status-sync-pattern.md 1.3 KB
- references/changelog-best-practices.md 17 KB
- references/code-commenting-guide.md 17 KB
- references/code-graph-documentation-patterns.md 499 B
- references/contributing-guide-standards.md 20 KB
- references/docs-as-code-setup.md 17 KB
- references/documentation-metrics.md 6.1 KB
- references/documentation-testing.md 26 KB
- references/markdown-style-guide.md 10 KB
- references/onboarding-documentation.md 7.1 KB
- references/production-gotchas-guide.md 9.8 KB
- references/readme-best-practices.md 13 KB
- references/runbook-writing-guide.md 7.1 KB
- references/writing-best-practices.md 25 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.
- 3d ago First seen · 238 lines · 36 tokens per session scan A b07e1095d1db
docs-codebase is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (82 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 3,206 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
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
ws-ckpt
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint，仅限 Linux; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"对比快照"、"快照改了什么"时 diff; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。.
compute-methods
Environment-verified friction sheets for field-standard computational tools (Rydberg pair interactions, QEC circuits, qLDPC decoding, code distance, atom dynamics, optics, quantum chemistry). Each sheet lists the tools the field actually uses, the first-use frictions that make agents wrongly abandon them, and one-line…