Skip to content

alirezarezvani/claude-skills / engineering/skills/agent-run-forensics

agent-run-forensics

Verified

Use when asked why an agent did something, what a past session or run changed, whether tests really passed, or to verify a session summary. Answers from the recorded transcript, not memory, with trace_finder.py, trace_timeline.py and claim_checker.py.

assets/forensic_answer_template.md

View on GitHub
# Answer template: a question about a past run

**Run:** `<session id>` (`<harness>`, `<start> -> <end>`), source `<path>`

**Answer (recorded):** One or two sentences, each citing a step.
> Step 9 ran `sed -i '...; s/timeout: 30/timeout: 5/' config.yaml` (exit 0). Nothing
> else in the run wrote config.yaml.

**Likely cause (inferred, with rule):**
> It followed the failed test at step 7 (retry-after-failure). The agent's own note
> at the time: "The test expects 3 retries; the config says 0. Setting it." The
> timeout change is not mentioned anywhere in the run.

**Not in the trace:** what the recording cannot answer (e.g. whether this config
was deployed).

**Correction, if an earlier account was wrong:** what was said, what the steps show.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall