Amadeus security patch

Skill amadeus-dlc/amadeus/dist/claude/.claude/skills/amadeus-security-patch

Agent skills, templates, examples, validators, and docs for operating Amadeus DLC, a lifecycle contract for AI driven software development.

Install

npx -y skills add amadeus-dlc/amadeus --skill amadeus-security-patch

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run the AI-DLC workflow with the security-patch scope baked in — no scope detection. CVE response. Packaging over `/amadeus --scope security-patch`, which works without this skill.

SKILL.md

1.6 KB, 326 tokens by cl100k_base, as published. Nobody here has run it

AI-DLC — security-patch scope

Drive the AI-DLC engine with the security-patch scope fixed. This is the same deterministic forwarding loop the /amadeus orchestrator runs, with --scope security-patch baked into the first next so scope detection is skipped. The engine owns all routing; the conductor persona arrives on the first directive's conductor_persona field — adopt it for the whole run.

The loop

directive = bun .claude/tools/amadeus-orchestrate.ts next --scope security-patch $ARGUMENTS
Act on directive.kind exactly as the orchestrator does (run-stage / ask / print / error / done) — see amadeus-common/protocols/stage-protocol.md.
bun .claude/tools/amadeus-orchestrate.ts report --stage <directive.stage> --result <outcome> [--user-input "<text>"] when the directive names a stage; omit --stage only for non-stage report round-trips.
Repeat from step 1 until directive.kind == done.

Pass $ARGUMENTS through verbatim after --scope security-patch; the engine parses any flags (--status, --stage, …) and the --scope from the state file always wins on an existing workflow, so re-running a started workflow resumes it. To run a different scope, use /amadeus --scope <other> instead.

Gives 0 of the 12 instructions most security skills give in 326 tokens

Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07

Parameterize all database queriesin 68 of 648, across 51 files
Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
Configure security headersin 35 of 648, across 19 files
Validate all inputsin 32 of 648, across 24 files
Validate all external input at the system boundaryin 29 of 648, across 19 files
Run containers as a non-root userin 28 of 648, across 15 files
Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
Run dependency audits before every releasein 21 of 648, across 10 files
Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
Copy dependencies before source codein 20 of 648, across 9 files
Store secrets in environment variablesin 20 of 648, across 18 files

Said here and by no other author read

adopt the conductor persona for the entire run
pass --scope security-patch as the first argument
forward arguments verbatim after the scope flag
act on directive.kind exactly as the orchestrator does
send report when the directive names a stage
omit --stage only for non-stage report round-trips

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.