Borrowing it
Nothing to install: this file belongs to EastStarAI/sanad-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/sanad-repository-maintainer/SKILL.mdgit clone --depth 1 https://github.com/EastStarAI/sanad-agentWrote 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/eaststarai/sanad-agent/sanad-repository-maintainer)<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-repository-maintainer"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-repository-maintainer/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/eaststarai/sanad-agent/sanad-repository-maintainer"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-repository-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01057 |
| Opus 5.5 | $0.00014 | $0.00423 |
| Sonnet 5.5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
Sanad Repository Maintainer 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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanad Repository Maintainer
Use this skill when maintaining EastStarAI/sanad-agent. It is written for human maintainers and for development agents acting on their behalf. Read-only inspection is safe by default. An agent must obtain explicit authorization from the responsible human before any GitHub mutation.
Start With Repository State
- Confirm the target repository, authenticated GitHub account, available repository role, default branch, and current commit.
- Read
.github/GOVERNANCE.mdand the nearest tracked manifest or documentation page for the surface being maintained. - Compare tracked desired state with the live repository before proposing a mutation.
- Report drift, missing permission, and rollback impact before changing live state.
- Query the postcondition after every mutation; an accepted API request is not evidence that the intended state is live.
Never hardcode mutable rule, category, run, branch, webhook, or secret identifiers. Discover them from the target repository when needed.
Permission Boundary
GitHub roles and organization policies may change. Verify the live permission instead of assuming it from a username.
- Public/read access may inspect metadata, Issues, Discussions, pull requests, checks, workflows, and other public repository state.
- Triage-capable maintainers may classify work and manage ordinary labels or Issue/Discussion state within project governance.
- Write or maintain access may update review branches and merge an eligible pull request when project policy and human authorization allow it.
- Administrative repository settings, branch protection or rulesets, Actions permissions, secrets, webhooks, security features, and organization-owned surfaces require the corresponding live administrative permission and separate action-specific authorization.
If the authenticated role cannot perform an operation, stop. Do not seek a bypass, weaker setting, alternate token, or unrelated organization permission.
Pull Requests and Protected Review
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.
- yesterday Changed 726d6cf4d612
- 2mo ago First seen · 62 lines · 35 tokens per session scan A 851f75420e1b
Sanad Repository Maintainer is a skill published in the GitHub repository EastStarAI/sanad-agent (47 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,057 once invoked, about $0.0001 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.
Sanad Repository Maintainer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Sanad Repository MaintainerEastStarAI/sanad-agent | Skill | 47 | yesterday | MIT | A | 35 | Claude Code, Codex |
| release-changelog-harnessArenukvern/mcp_flutter | Skill | 395 | 20d ago | MIT | A | 84 | Claude Code |
| gitnexus-cliArenukvern/mcp_flutter | Skill | 395 | 20d ago | MIT | A | 59 | Claude Code |
| he-shipsgaabdu4/building-flutter-apps | Skill | 25 | 4d ago | MIT | A | 52 | Claude Code |
| code-reviewsgaabdu4/building-flutter-apps | Skill | 25 | 4d ago | MIT | A | 39 | Claude Code, Codex |
| flutterpledgeandgrow/pledge-skills | Skill | 10 | 3mo ago | MIT | A | 126 | Claude Code, Codex |
| autofix-prQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 141 | Claude Code |