nixos-config: Skill for Claude Code

.agents/skills/repo-map-query/SKILL.md

repo-map-query is a skill for Claude Code, Codex from FilipNowakowicz/nixos-config. It costs 32 tokens per session (409 once invoked), scanned A, original, MIT.

A repository-search helper that uses a generated map of a codebase to suggest which files to inspect first.

In plain words
What is it for?
Use it before broad code exploration to locate likely modules, scripts, checks, hooks, tests, or configuration files, then verify the results in the actual files.
Why use it?
It reduces the need to search through a large repository blindly when the relevant files are not obvious.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is FilipNowakowicz/nixos-config's own configuration. It tells Claude Code and Codex how to work on nixos-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nixos-config configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .agents/repo-map/scripts/query.sh merge-gate lint.

Reuse

Borrowing it

Nothing to install: this file belongs to FilipNowakowicz/nixos-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FilipNowakowicz/nixos-config/main/.agents/skills/repo-map-query/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FilipNowakowicz/nixos-config

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for repo-map-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/repo-map-query/github.svg)](https://agentmods.dev/skills/filipnowakowicz/nixos-config/repo-map-query)
Your own site
<a href="https://agentmods.dev/skills/filipnowakowicz/nixos-config/repo-map-query"><img src="https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/repo-map-query/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.

agentmods 80×15 button for repo-map-query

Your own site · 80×15
<a href="https://agentmods.dev/skills/filipnowakowicz/nixos-config/repo-map-query"><img src="https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/repo-map-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00409
Opus 5 $0.00016 $0.00204
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 11d ago against content hash 8e77b03eb8a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

repo-map-query 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 11d 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.

.agents/skills/repo-map-query/SKILL.md · 47 lines

What it actually says

Repo Map Query

Use .agents/repo-map/scripts/query.sh to find likely files before broad manual exploration. This is a routing helper, not a source of truth.

When to use

  • The user asks about a repo feature and the owning files are not obvious.
  • You are about to open broad docs only to discover paths.
  • You are about to run a wide rg and then paste many results into context.
  • You need to connect task words to repo areas, hosts, checks, modules, hooks, packages, or tests.

Skip this when the exact file is already known.

Workflow

  1. Build 2-6 concrete query terms from the task: command names, host names, service names, checks, modules, scripts, or error words.
  2. Run bash .agents/repo-map/scripts/query.sh <terms>.
  3. Open only the top few plausible files.
  4. Verify the answer or edit against the real files.

Examples:

bash .agents/repo-map/scripts/query.sh merge-gate lint
bash .agents/repo-map/scripts/query.sh homeserver-gcp sops bootstrap
bash .agents/repo-map/scripts/query.sh waybar theme switch

Guardrails

  • Do not treat query output as authoritative. It only says where to look first.
  • Do not add repo-map output to normal summaries unless it explains a decision.
  • Keep query terms specific; vague terms like config or module produce weak routing.
  • If the routed files don't resolve the question and broader exploration is still needed (many greps/reads across unfamiliar areas), prefer dispatching an Explore subagent and bringing back only its conclusion, rather than letting many raw search results accumulate in this session's transcript.
Changes

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.

  1. 11d ago First seen · 47 lines · 32 tokens per session scan A 8e77b03eb8a3

Subscribe to this mod's changes

repo-map-query is a skill published in the GitHub repository FilipNowakowicz/nixos-config (5 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 409 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 2026-08-31.