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 writing-plansgit 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/writing-plans)<a href="https://agentmods.dev/skills/ganyuanran/aegis/writing-plans"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/writing-plans/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/writing-plans"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 450 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.05232 |
| Opus 5 | $0.00022 | $0.02616 |
| Sonnet 5 | $0.00009 | $0.01046 |
| Haiku 4.5 | $0.00004 | $0.00523 |
Grade A, and why
writing-plans 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 7d 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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute
→ Have an existing parent plan/spec and a tiny execution slice? → Use Planless Slice Lane.
- Emit a compact Slice Card: goal, parent plan/spec, files, boundary, verification, stop
- Update the parent workstream checkpoint/evidence/drift state if persistent state is needed
- Do not save a new plan for the micro-slice → Mechanical or bounded change with no durable boundary (no new owner, contract, schema, public API, migration, or compat surface)? → Use Planless Slice Lane without a parent document. Emit the compact Slice Card, skip the plan file, and record the change in the commit message. → Have approved spec/requirements for a new workstream or an escalation trigger? → Write implementation plan. Assume engineer has zero context.
- Scope check: fact/assumption/unknown, baseline, Requirement Ready Check, Ripple Signal Triage, compatibility boundary, dual-track needs
- File map: what files created/modified, clear boundaries, follow existing patterns
- Bite-sized tasks (2-5 min each): exact file paths, complete code, exact commands, expected output
- Self-review: spec coverage, placeholders, type consistency, compatibility, verification, dual-track
- Save → select and announce the execution route; proceed unless a real authorization or safety boundary requires the user → Plan must answer: problem, baseline, files, compat, verification, risks, retirement. → Escalate from Planless Slice Lane to a durable plan when the slice adds a new owner, contract, schema, public API, architecture boundary, migration, persistence, security/permission, distribution/release surface, or unclear verification boundary.
What ships with it
1 file 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.
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.
- 7d ago Changed · +9 lines 91771c98e105
- 11d ago First seen · 490 lines · 44 tokens per session scan A e0794871f909
writing-plans is a skill published in the GitHub repository GanyuanRan/Aegis (1,178 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 5,232 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.