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 skills add babarot/gh-infra --skill repository-manifestgit clone --depth 1 https://github.com/babarot/gh-infraWrote 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/babarot/gh-infra/repository-manifest)<a href="https://agentmods.dev/skills/babarot/gh-infra/repository-manifest"><img src="https://agentmods.dev/badge/skills/babarot/gh-infra/repository-manifest/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/babarot/gh-infra/repository-manifest"><img src="https://agentmods.dev/badge/skills/babarot/gh-infra/repository-manifest.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 | $0.00045 | $0.01231 |
| Opus 5.5 | $0.00018 | $0.00492 |
| Sonnet 5.5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
repository-manifest 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manifest Reference
Use this skill when editing repository-side manifests. Keep the body small and load references only as needed.
Core Rules
- All
specfields are optional. Omitted fields are left unchanged on GitHub. Repositorymanages one repository.RepositorySetmanages many repositories with shareddefaults.- For new setups, prefer
rulesetsover classicbranch_protection. - Secret values must use
${ENV_*}indirection, never literal secrets.
Repository
apiVersion: gh-infra/v1
kind: Repository
metadata:
owner: my-org
name: my-repo
reconcile: # optional; controls collection reconciliation
rulesets: additive # additive (default) | authoritative
labels: additive
spec:
# declare only managed fields
Read these references as needed:
- General settings and lifecycle: references/general.md
- Labels and reconcile mode: references/labels.md
- Actions settings and validation traps: references/actions.md
- Rulesets and branch protection: references/protection.md
- Secrets and variables: references/secrets-variables.md
- Deployment environments: references/environments.md
- Security (Dependabot, vulnerability alerts): references/security.md
- GitHub Pages (build type, source, domain, HTTPS): references/pages.md
RepositorySet
Use RepositorySet when many repositories share defaults.
apiVersion: gh-infra/v1
kind: RepositorySet
metadata:
owner: my-org
defaults:
reconcile:
rulesets: authoritative
labels: additive
spec:
visibility: public
features:
wiki: false
merge_strategy:
allow_squash_merge: true
allow_rebase_merge: false
auto_delete_head_branches: true
rulesets:
- name: protect-main
target: branch
enforcement: active
conditions:
ref_name:
include: ["refs/heads/main"]
rules:
pull_request:
required_approving_review_count: 1
non_fast_forward: true
repositories:
- name: repo-a
spec:
description: "Service A"
topics: [go, api]
- name: repo-b
spec:
description: "Service B"
topics: [python, cli]
features:
wiki: true
What ships with it
10 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.
- references/actions.md 1.4 KB
- references/environments.md 3.6 KB
- references/general.md 3.1 KB
- references/labels.md 1009 B
- references/milestones.md 1.6 KB
- references/pages.md 2.6 KB
- references/protection.md 4.2 KB
- references/repository-set.md 2.3 KB
- references/secrets-variables.md 592 B
- references/security.md 1.5 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.
- 9d ago Changed · +1 lines c1b1d0e8d222
- 11d ago Changed · +5 lines · +2 tokens per session b6abda7fc3ef
- 1mo ago Changed · +4 lines d79800ec9028
- 2mo ago First seen · 120 lines · 43 tokens per session scan A fe3b2b6329fa
repository-manifest is a skill published in the GitHub repository babarot/gh-infra (152 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 1,231 once invoked, about $0.0002 per session on Opus 5.5. 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.
repository-manifest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repository-manifestbabarot/gh-infra | Skill | 152 | 3d ago | MIT | A | 45 | Claude Code, Codex |
| gh-attachsudosubin/gh-attach | Skill | 45 | today | MIT | A | 94 | Claude Code, Codex |
| gh-stackgithub/gh-stack | Skill | 1.8k | 6d ago | MIT | A | 80 | Claude Code, Codex |
| pkup-enchantpPrecel/pkup-gen | Skill | 12 | 3mo ago | MIT | A | 59 | Claude Code, Codex |
| vhs-e2e-gifdimetron/pi-go | Skill | 224 | yesterday | MIT | A | 106 | Claude Code, Codex |
| check-linters-before-commitdimetron/pi-go | Skill | 224 | yesterday | MIT | A | 30 | Claude Code, Codex |
| ghtknsuzuki-shunsuke/ghtkn | Skill | 462 | yesterday | MIT | A | 146 | Claude Code, Codex |