CtrlK
BlogDocsLog inGet started
Tessl Logo

coding-agent-helpers/compact-debug-ledger

Use when a debugging thread needs to be compressed into a reusable investigation ledger. Capture the target, evidence, attempted fixes, ruled-out hypotheses, viable hypotheses, and next experiments. Good triggers include "compact this debugging session", "summarize what we've tried", and "turn this into a debugging ledger".

99

3.66x
Quality

100%

Does it follow best practices?

Impact

99%

3.66x

Average score across 8 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-5/

{
  "context": "Tests whether the agent produces a Debug Target section that is exactly one sentence, even when the incident involves multiple interacting systems that could tempt a verbose multi-sentence description.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Debug Target section present",
      "description": "Output contains a '### Debug Target' section header",
      "max_score": 8
    },
    {
      "name": "Debug Target is one sentence",
      "description": "The content under Debug Target is exactly one sentence — it ends with a single period (or equivalent) and does not contain multiple sentences separated by periods, semicolons acting as sentence breaks, or bullet points",
      "max_score": 20
    },
    {
      "name": "Debug Target captures essence",
      "description": "The single-sentence Debug Target meaningfully describes the core incident (e.g. references the cascading failure, the ES/SendGrid combination, or the user-visible symptoms) rather than being a generic placeholder",
      "max_score": 12
    },
    {
      "name": "Evidence section",
      "description": "Output contains an '### Evidence' section as a bullet list",
      "max_score": 8
    },
    {
      "name": "Attempts section",
      "description": "Output contains an '### Attempts' section where items have worked/failed/inconclusive labels",
      "max_score": 10
    },
    {
      "name": "Ruled Out section",
      "description": "Output contains a '### Ruled Out' section",
      "max_score": 8
    },
    {
      "name": "Still Plausible section",
      "description": "Output contains a '### Still Plausible' section",
      "max_score": 8
    },
    {
      "name": "Next Experiments section",
      "description": "Output contains a '### Next Experiments' section with 1-3 items",
      "max_score": 8
    },
    {
      "name": "No chronological replay",
      "description": "Output is NOT structured as a timestamped chronological replay of the war room — it uses the Evidence/Attempts/Hypotheses structure instead",
      "max_score": 10
    },
    {
      "name": "File saved",
      "description": "A file named incident_record.md exists in the workspace",
      "max_score": 8
    }
  ]
}

evals

tile.json