Aegis is a method pack that guides coding agents to inspect a project's baseline, make bounded changes, and verify their work with fresh evidence. It is for people using coding-agent hosts who want fewer unverified changes and less unnecessary process. The catalogue add-ons implement this method through skills, instructions, commands, a hook, and a plugin.
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 GanyuanRan/Aegis --skill finishing-a-development-branchgit clone --depth 1 https://github.com/GanyuanRan/AegisWrote 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/ganyuanran/aegis/finishing-a-development-branch)<a href="https://agentmods.dev/skills/ganyuanran/aegis/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/finishing-a-development-branch/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/ganyuanran/aegis/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/finishing-a-development-branch.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 | $0.00038 | $0.01102 |
| Opus 5 | $0.00019 | $0.00551 |
| Sonnet 5 | $0.00008 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
finishing-a-development-branch 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.
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.
Finishing a Development Branch
Overview
Integration choice and checkout lifetime are separate. Verify first, mutate only task-owned resources, then prove what was removed or retained.
Core principle: fresh evidence -> authorized integration -> ownership-aware cleanup -> Git/path readback.
Announce at start: explain which branch/worktree lifecycle is being closed.
Step 1: Environment and Ownership Detection
Read the task's TaskStartSnapshot and current repository state. Record:
- root,
HEAD, branch/detached state, upstream divergence, and active Git ops; - staged/unstaged/untracked paths and the task-owned delta;
git worktree list --porcelain;- branch/worktree creator, task ownership, base branch, and cleanup trigger.
Stop on conflicts, detached state, failed verification, dirty/untracked state in
a cleanup target, or unknown ownership. Do not infer the base from the names
main or master; use task records, repository authority, or explicit user
direction. Never auto-stash, reset, clean, pull, rebase, amend, force-push, or
bypass hooks.
If no task-created branch/worktree exists and integration was not requested,
skip this workflow: report the local task commit plus Task clean and
Repository clean; do not invent merge/PR ceremony.
Step 2: Fresh Verification
Run the smallest current-authority test set that proves the completed task. If it fails, preserve all work and return to diagnosis. Do not present the branch as ready.
Step 3: Choose the Authorized Outcome
When a task branch actually needs disposition, present only applicable choices:
- merge into the recorded base locally;
- push and create/update a PR;
- keep the branch for later integration;
- discard the exact task-owned branch/worktree.
Push, PR, remote deletion, release, and force operations require explicit user authorization. Discard requires a fresh, exact typed confirmation naming branch, worktree path, and commits/delta to lose. Generic agreement is insufficient.
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.
- 11d ago First seen · 130 lines · 38 tokens per session scan A 995a2a17fdb5
finishing-a-development-branch is a skill published in the GitHub repository GanyuanRan/Aegis (1,178 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,102 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 2026-08-30.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…
prs-awaiting-author
List open pull requests where the ball is in the author's court: CI is failing, review comments are unaddressed, or a maintainer question is awaiting the author's reply. Use when the user wants to see PRs awaiting author action.