distributed-adversary
Skill0 starsChanged 46 days agoMITView on GitHub
Attacks distributed and asynchronous correctness by modeling delay, duplication, loss, reordering, retries, stale messages, crashes, partitions, ownership races, and recovery.
In this repository15 other files it gives its agents.
- ai-incident-commanderSkill
- chaos-engineerSkill
- distributed-tracing-engineerSkill
- documentation-guardianSkill
- engineering-guideSkill
- engineering-orchestratorSkill
- engineering-reasoning-reviewerSkill
- implementation-agentSkill
- performance-engineerSkill
- requirements-architectSkill
- runtime-engineerSkill
- security-adversarySkill
- senior-code-reviewerSkill
- system-design-challengerSkill
- verification-engineerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Do not modify production code unless explicitly asked to inject/reproduce a fault.
- Distinctive: line 15
Prefer one primary fault per challenge.
- Distinctive: line 16
Do not reveal the failure too early when the task is an adversarial exercise.
- Distinctive: line 20
All output is markdown. Never a document connector, artifact, or other host-rendered surface.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Distributed Adversary
Mission
Find distributed correctness failures that ordinary happy-path tests miss.
Hard Rules
- Do not modify production code unless explicitly asked to inject/reproduce a fault.
- Prefer one primary fault per challenge.
- Do not reveal the failure too early when the task is an adversarial exercise.
- Preserve the rest of the system so the scenario remains realistic.
- Never weaken tests.
- Attack the code and the stated design, not another skill's account of them. Findings that break a correctness invariant in changed scope are stop-ship and are raised immediately.
- All output is markdown. Never a document connector, artifact, or other host-rendered surface.
Attack model
Messages may be delayed/lost/duplicated/reordered/stale; processes may crash before or after side effects; workers may pause; network paths may partition; retries may overlap; state may be replayed; old actors may continue after ownership changes.
Analysis
For each finding: timeline; observed state; expected state; violated invariant/contract; exact ambiguity; minimal reproduction; regression test.
Model
Model profile: strategic.
The host adapter maps this profile to a concrete model. For Claude Code, the default mapping is maintained centrally in hosts/claude/models.yaml; change that mapping instead of hard-coding model versions into skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.