Analyze Agents
Read-only autopsy of agent config, traces, failure modes.
What it is
Section titled “What it is”Read-only autopsy of agent config, traces, failure modes. This practice is a skill-mapped TTP: when, why, and which command—not a full copy of the skill. Open the skill to execute.
Why it works
Section titled “Why it works”You cannot improve what you do not observe. SRE and DevOps both insist on evidence before change; agent systems need the same: traces of tool calls, failure modes, and stop-condition gaps. NIST AI RMF’s Map/Measure steps put diagnosis before govern-by-vibes rewrites.
When to use it
Section titled “When to use it”When the situation matches the one-liner above and Orientation (or your project path) says this is the fire to touch now.
- Invoke the skill; follow its safety rules
- Keep one write owner; collect evidence before claiming done
- Hand off to the next practice instead of boiling the ocean
- Skip orientation when you’re lost
- Spawn overlapping agents to “go faster”
- Treat the practice as done without evidence
Related concepts
Section titled “Related concepts”05-agent-agency, 04-evidence-over-vibes
Further reading
Section titled “Further reading”See also the handbook Sources & grounding bibliography.
Agent skill
Section titled “Agent skill”agents analyze