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-8/

{
  "context": "Tests whether the agent retains only enough implementation detail to support the next experiment, rather than reproducing full code snippets, exhaustive call-site lists, and exploratory dead-end code from the investigation history.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "No full code blocks",
      "description": "Output does NOT reproduce multi-line code blocks (fenced ``` blocks) from the investigation notes — implementation detail is described in prose or brief references, not copy-pasted code",
      "max_score": 18
    },
    {
      "name": "No exhaustive call-site list",
      "description": "Output does NOT list all 14 individual call sites with file names and line numbers — the fact that downstream code required updating is sufficient without enumerating every location",
      "max_score": 12
    },
    {
      "name": "Key insight preserved",
      "description": "Output retains the essential insight: Go omitempty on a pointer field produces events without user_id, but the Rust struct expected a non-optional String",
      "max_score": 12
    },
    {
      "name": "Attempts section with labels",
      "description": "Output contains an '### Attempts' section where each attempt has a worked/failed/inconclusive label",
      "max_score": 10
    },
    {
      "name": "Evidence section",
      "description": "Output contains an '### Evidence' section as a bullet list",
      "max_score": 8
    },
    {
      "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 referencing the open questions (other event types with same mismatch, schema validation layer)",
      "max_score": 8
    },
    {
      "name": "Next Experiments section",
      "description": "Output contains a '### Next Experiments' section with 1-3 items (not more)",
      "max_score": 8
    },
    {
      "name": "Debug Target one sentence",
      "description": "Output contains a '### Debug Target' section with exactly one sentence",
      "max_score": 8
    },
    {
      "name": "File saved",
      "description": "A file named rust_debug.md exists in the workspace",
      "max_score": 8
    }
  ]
}

evals

tile.json