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 recording-architecture-decisionsgit 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/recording-architecture-decisions)<a href="https://agentmods.dev/skills/ganyuanran/aegis/recording-architecture-decisions"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/recording-architecture-decisions/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/recording-architecture-decisions"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/recording-architecture-decisions.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 | $0.00048 | $0.01321 |
| Opus 5 | $0.00024 | $0.00660 |
| Sonnet 5 | $0.00010 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
recording-architecture-decisions 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording Architecture Decisions
Purpose
Record durable architecture decisions without losing the current-state baseline closure. An ADR records why a decision was made; a baseline records what the architecture is after that decision.
This skill is a lazy, task-specific workflow. It does not replace
verification-before-completion, does not grant completion authority, and does
not make authoritative GateDecision or PolicySnapshot outputs.
Required Read Set
Before deciding or writing, read the smallest relevant excerpts from:
docs/adr/ADR-CREATION-GATE.mddocs/current/AEGIS_ADR_AUTO_BACKFILL.md- the target project's current ADR, baseline, or authority docs that own the affected architecture surface
For Aegis repository changes, use this repository's docs/adr/ and
docs/current/ authority order. For target projects with their own ADR system,
respect that project owner instead of duplicating the same decision into
docs/aegis/adr/.
When To Use
Use this skill when the user asks to:
- create, write, update, amend, supersede, or evaluate an ADR
- decide whether an architecture decision record is needed
- record a durable architecture decision or decision log entry
- close baseline sync after an ADR-relevant architecture change
- verify that an ADR action did not leave the architecture baseline stale
Do not use it for simple wording edits, ordinary README cleanup, tests-only coverage improvements, low-risk single-file changes, or bug fixes that only restore the existing baseline.
Decision Flow
- Identify the decision candidate and evidence source.
- Run the ADR creation gate:
- hard to reverse
- surprising without context
- real trade-off
- Apply the Retro / Memory Filter:
- executed durable decisions may become ADR or baseline memory
- unexecuted ideas stay out of accepted architecture memory
- process notes may use a lighter record when they do not change current architecture state
- Choose exactly one ADR action: create, amend, supersede, or skip.
- Choose the owner surface: project
docs/adr/,docs/aegis/adr/, existing ADR, or lighter record. - Run Baseline Sync Closure.
- If writing files, preserve local ADR conventions and verify structure.
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 · 156 lines · 48 tokens per session scan A 188c32797305
recording-architecture-decisions is a skill published in the GitHub repository GanyuanRan/Aegis (1,178 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,321 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.
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…
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.