teguma: Skill for Codex

.agents/skills/repo-development-os/SKILL.md

repo-development-os is a skill for Codex from Doyajin174/teguma. It costs 37 tokens per session (1,030 once invoked), scanned A, original, MIT.

A small repository routine that checks required Git and GitHub project state before development and records release information using version numbers.

In plain words
What is it for?
Use it to install the routine, run a read-only preflight check, review findings, and maintain release records following semantic versioning.
Why use it?
It catches missing or unfinished repository setup before new work begins without adding background services or automatic fixers.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

This is Doyajin174/teguma's own configuration. It tells Codex how to work on teguma 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 teguma configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Doyajin174/teguma. 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/Doyajin174/teguma/main/.agents/skills/repo-development-os/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Doyajin174/teguma

Made for: 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-development-os

README.md
[![agentmods](https://agentmods.dev/badge/skills/doyajin174/teguma/repo-development-os/github.svg)](https://agentmods.dev/skills/doyajin174/teguma/repo-development-os)
Your own site
<a href="https://agentmods.dev/skills/doyajin174/teguma/repo-development-os"><img src="https://agentmods.dev/badge/skills/doyajin174/teguma/repo-development-os/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-development-os

Your own site · 80×15
<a href="https://agentmods.dev/skills/doyajin174/teguma/repo-development-os"><img src="https://agentmods.dev/badge/skills/doyajin174/teguma/repo-development-os.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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 $0.00037 $0.01030
Opus 5 $0.00018 $0.00515
Sonnet 5 $0.00007 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 10d ago against content hash 251113af368f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

repo-development-os 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/repo_os.py, tests/test_repo_os.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-development-os/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Development OS

Use existing Git, GitHub, Codex, and repository files. The routine is strict; its implementation is small. Do not add a daemon, hook, database, dashboard, scheduled scan, automatic fixer, global Codex state, or an all-in-one command.

Install

python3 <source-skill>/scripts/repo_os.py install --repo <path-inside-target-repo>

Installation adds the local skill, the managed AGENTS.md and pull-request blocks, and missing starter files. It preserves project-specific text and can be rerun. Use --dry-run to preview.

Start every substantive task

python3 .agents/skills/repo-development-os/scripts/repo_os.py preflight --repo .
  • Exit 0: required local and GitHub state was verified and no cleanup finding exists.
  • Exit 1: report the findings, clear them before new work, and rerun preflight.
  • Exit 2: required state could not be verified; report the gap and stop.

Preflight only reads the selected repository. It never mutates Git, GitHub, issues, pull requests, tags, releases, or worktrees.

Practical routing

  • Prioritize the user's observable completion scenario and smooth real use. Keep planning and implementation to the smallest sufficient scope, but never skip, combine, or reorder a mandatory routine step.
  • Load and follow tidy without waiting for the user to name it when the task's actual goal is repository-wide structure, governance, documentation conventions, duplication, or cleanup. Do not attach a broad tidy pass to ordinary feature or fix work, and do not expand the issue scope.
  • When docs/code-atlas exists and work locates or changes a mapped concept, load and follow maintain-code-atlas without waiting for the user to name it. Revalidate current sources first and update only directly affected cards during authorized implementation. Never bulk-create or refresh unrelated cards.

Normal sequence

  1. Use one issue containing a Goal, Completion scenario, and measurable Acceptance criteria.
  2. Check current code and pull requests, research authoritative internet sources, and write a compact specification.
  3. Use one codex/issue-N-slug branch and one clean linked worktree under the stable sibling root. Update from main before measurement.
  4. Implement the smallest change that satisfies the issue.
  5. Open one human-readable pull request. It closes at most 3 issues, changes at most 50 files, uses #N in every change commit, and contains Closes #N.
  6. Read the full diff once for self-review.
  7. Run one independent read-only AI review.
  8. Apply one fixup round when findings exist and rerun relevant checks.
  9. Squash merge.
  10. Update main, remove the issue worktree and branch, confirm issue closure, and decide release.

Read the full file on GitHub · 102 lines

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. 10d ago First seen · 102 lines · 37 tokens per session scan A 251113af368f

Subscribe to this mod's changes

repo-development-os is a skill published in the GitHub repository Doyajin174/teguma (0 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,030 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.