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 goal-framinggit 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/goal-framing)<a href="https://agentmods.dev/skills/ganyuanran/aegis/goal-framing"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/goal-framing/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/goal-framing"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/goal-framing.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 | $0.00046 | $0.01054 |
| Opus 5 | $0.00023 | $0.00527 |
| Sonnet 5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
goal-framing 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aegis Goal Framing
Use this skill to create a thin goal frame before execution. It is opt-in and boundary-setting only.
Do not use it for tiny edits, one-command checks, or ordinary fast-path Q&A
unless the user explicitly asks for /aegis-goal or Aegis goal:.
Authority Boundary
Current owner:
- Method Pack task framing
Not owned here:
- authoritative
GateDecision - final evidence sufficiency
- final completion authority is not owned here
- host daemon / automatic stop enforcement
Input Forms
Treat these as equivalent:
/aegis-goal <task description>Aegis goal: <task description>- "Define the goal / stop condition before we start"
Slash commands are optional host shortcuts. The natural-language form is the portable fallback.
Example:
Aegis goal: Fix the auth refresh bug without rewriting the auth system.
Output
Produce the smallest useful frame, then continue into the routed workflow in the same turn.
TaskIntentDraft:
- Requested outcome:
- Goal:
- Success evidence:
- Stop condition:
- Non-goals:
- Constraints:
- Scope:
- Risk hints:
- Aegis Visibility:
- Route:
- Next:
Default behavior:
- Do not stop after
TaskIntentDraft. - Treat the frame as the start protocol for execution, not as the final answer.
- After the compact frame, immediately take the
Nextaction for the selected route when the user asked to do the work. - Keep the visible frame natural and short when the goal is clear; do not emit a large internal-looking card unless the user asked for a formal frame.
- Use
Aegis Visibilityto say why the goal frame constrains the route, stop condition, or non-goals. Do not add trace ceremony unless the user explicitly asks for auditability.
Frame-only behavior:
- Stop at the frame only when the user explicitly asks to only define the goal, only define the stop condition, not execute, not implement, not write a plan, or wait for confirmation before continuing.
- If required information is missing, state the missing input and stop with
blockedrather than pretending to continue.
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 · 151 lines · 46 tokens per session scan A 24208ea7e3d6
goal-framing is a skill published in the GitHub repository GanyuanRan/Aegis (1,178 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,054 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.