Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jarroslav/agentic-os/plugin install agentic-sdlcWrote 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/jarroslav/agentic-os/repo-guides)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/repo-guides"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/repo-guides/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/repo-guides"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/repo-guides.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00175 | $0.03655 |
| Opus 5 | $0.00088 | $0.01827 |
| Sonnet 5 | $0.00035 | $0.00731 |
| Haiku 4.5 | $0.00017 | $0.00365 |
Grade A, and why
repo-guides 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 10d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-guides
One-time onboarding that turns a repository into a knowledge base coding agents can read. You survey the repo, get user sign-off on a plan, render a curated guide tree under .agentic/guides/, and idempotently connect it to the project's assistant entrypoint.
.agentic/guides/is the single source of guidance consumed by every agentic-sdlc skill and agent. Do not create a parallel doc tree. Everything you generate lands here or in the entrypoint files.
Blast radius
R2 — you write tracked repo files (the guide tree and the entrypoint) plus one R1 run-artifact (the local run journal). No R3 external side-effects: no git operations, no network, no tooling install. Every write is gated behind explicit user approval.
When to use
- User is bootstrapping a repo for AI-assisted work and asks for repo guides / an entrypoint.
- Trigger phrases: "repo guides", "set up repo guides", "agentic init", "create AGENTS.md", "wire the AI entrypoint".
Run the repo-audit-guides skill (R0, read-only) FIRST on any brownfield repo. It emits the # Repo Knowledge Audit this skill consumes. On a truly empty/greenfield repo you may proceed without an audit, but the halt conditions below still apply.
Inputs
| Input | Source | Required |
|---|---|---|
| Audit report | repo-audit-guides output, marker # Repo Knowledge Audit |
brownfield: yes |
| Repo signals | manifests, git remote -v, git log --oneline -10, .pre-commit-config.yaml, CI files, Makefile, pyproject.toml, package.json, tox.ini, setup.cfg |
detected, not asked |
| User decisions | plan approval, per-file entrypoint diffs, gate/adapter confirmations | interactive |
Detection before prompt, everywhere. Read the repo before you ask a question; only ask about what detection cannot resolve.
Audit contract (consumed)
The report carries marker # Repo Knowledge Audit and these sections: Where the docs live, How usable the docs are, Assistant instruction files, Agents, skills and hooks, Where they disagree, Ready to plant?, Evidence. Per-item verdict vocabulary: preserve / incorporate / merge / replace / skip / ask / halt.
What ships with it
15 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.
- evals/evals.json 6.8 KB
- README.md 1.9 KB
- references/entrypoint-wiring.md 11 KB
- references/plan-and-generate.md 13 KB
- references/survey.md 12 KB
- references/templates/guides/api/api-patterns.md.template 4.5 KB
- references/templates/guides/architecture/architecture.md.template 6.3 KB
- references/templates/guides/data/database-patterns.md.template 6.8 KB
- references/templates/guides/development/development-practices.md.template 6.6 KB
- references/templates/guides/integration/external-integrations.md.template 4.8 KB
- references/templates/guides/security/security-practices.md.template 9.1 KB
- references/templates/guides/standards/code-quality.md.template 4.6 KB
- references/templates/guides/standards/git-workflow.md.template 4.6 KB
- references/templates/guides/testing/testing-patterns.md.template 6.0 KB
- references/writing-guides.md 7.8 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.
- 10d ago First seen · 207 lines · 175 tokens per session scan A 823ecaf738a8
repo-guides is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 175 tokens to every session and 3,655 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…