@slowdini/slow-powers-opencode 0.2.0 → 0.4.0

package/skills/evaluating-skills/schema/run-record.schema.json

@@ -1,80 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "$id": "https://slow-powers.dev/schemas/run-record.schema.json",
-  "title": "Portable Run Record",
-  "description": "Captures one subagent run. Harness-agnostic — each harness writes an adapter from its native transcript format to this shape. Downstream grading reads only this file.",
-  "type": "object",
-  "required": [
-    "eval_id",
-    "condition",
-    "skill_path",
-    "prompt",
-    "files",
-    "final_message",
-    "tool_invocations"
-  ],
-  "additionalProperties": false,
-  "properties": {
-    "eval_id": {
-      "type": "string",
-      "description": "Matches the eval's id in evals.json."
-    },
-    "condition": {
-      "type": "string",
-      "description": "Reserved names: with_skill, without_skill, old_skill, new_skill."
-    },
-    "skill_path": {
-      "type": ["string", "null"],
-      "description": "Absolute path to the SKILL.md the subagent could load, or null if no skill was provided (without_skill condition)."
-    },
-    "prompt": {
-      "type": "string",
-      "description": "The user prompt as dispatched to the subagent."
-    },
-    "files": {
-      "type": "array",
-      "items": { "type": "string" },
-      "description": "Fixture files the subagent had access to (absolute paths inside the run's workspace)."
-    },
-    "final_message": {
-      "type": "string",
-      "description": "The agent's final user-facing text output."
-    },
-    "tool_invocations": {
-      "type": "array",
-      "description": "Ordered list of tool calls during the run.",
-      "items": {
-        "type": "object",
-        "required": ["name", "ordinal"],
-        "additionalProperties": false,
-        "properties": {
-          "name": {
-            "type": "string",
-            "description": "Tool name as recorded by the harness (e.g. Bash, Read, run_command). Adapters should preserve original names."
-          },
-          "args": {
-            "description": "Tool arguments. Object for structured tools, string for raw command-style tools.",
-            "type": ["object", "string", "array", "null"]
-          },
-          "result": {
-            "description": "Tool output, if captured. Truncate long outputs to ~2KB.",
-            "type": ["string", "object", "null"]
-          },
-          "ordinal": {
-            "type": "integer",
-            "minimum": 0,
-            "description": "0-indexed position in the run. Used by must_precede checks."
-          }
-        }
-      }
-    },
-    "total_tokens": {
-      "type": ["integer", "null"],
-      "description": "From the harness's task completion event. May be null if the harness does not surface this."
-    },
-    "duration_ms": {
-      "type": ["integer", "null"],
-      "description": "From the harness's task completion event. May be null if the harness does not surface this."
-    }
-  }
-}

package/skills/evaluating-skills/schema/stray-writes.schema.json

@@ -1,68 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "$id": "https://slow-powers.dev/schemas/stray-writes.schema.json",
-  "title": "Stray-Write Report",
-  "description": "Output of evals:detect-stray-writes. Flags subagent file writes / mutating commands that landed outside a run's outputs dir. Lives at <workspace>/iteration-N/stray-writes.json.",
-  "type": "object",
-  "required": ["generated", "iteration", "totals", "runs"],
-  "additionalProperties": false,
-  "properties": {
-    "generated": { "type": "string", "description": "ISO timestamp" },
-    "iteration": { "type": "integer" },
-    "totals": {
-      "type": "object",
-      "required": ["violations", "warnings"],
-      "additionalProperties": false,
-      "properties": {
-        "violations": { "type": "integer" },
-        "warnings": { "type": "integer" }
-      }
-    },
-    "runs": {
-      "type": "array",
-      "description": "One entry per (eval, condition) run that had at least one finding.",
-      "items": {
-        "type": "object",
-        "required": ["eval_id", "condition", "violations", "warnings"],
-        "additionalProperties": false,
-        "properties": {
-          "eval_id": { "type": "string" },
-          "condition": { "type": "string" },
-          "violations": {
-            "type": "array",
-            "description": "High-confidence: a write tool targeted a path outside the run's outputs dir.",
-            "items": { "$ref": "#/definitions/finding" }
-          },
-          "warnings": {
-            "type": "array",
-            "description": "Heuristic: a Bash command matched a mutating pattern (install, git, sed -i, redirection) without referencing the outputs dir.",
-            "items": { "$ref": "#/definitions/finding" }
-          }
-        }
-      }
-    }
-  },
-  "definitions": {
-    "finding": {
-      "type": "object",
-      "required": ["tool", "ordinal", "reason"],
-      "additionalProperties": false,
-      "properties": {
-        "tool": { "type": "string" },
-        "path": {
-          "type": "string",
-          "description": "Target path for write-tool violations."
-        },
-        "command": {
-          "type": "string",
-          "description": "Command text for Bash warnings."
-        },
-        "ordinal": {
-          "type": "integer",
-          "description": "Position of the invocation in the run's tool_invocations."
-        },
-        "reason": { "type": "string" }
-      }
-    }
-  }
-}

package/skills/evaluating-skills/templates/eval-task-prompt.md

@@ -1,67 +0,0 @@
-# Eval task dispatch template
-
-Use this template when dispatching a fresh general-purpose subagent to execute a single eval test case.
-
-**The subagent MUST start with clean context.** State from previous runs invalidates the comparison.
-
-## Variables to fill
-
-| Variable | Source |
-|---|---|
-| `{{eval_id}}` | The eval's `id` from `evals.json` |
-| `{{condition}}` | `with_skill`, `without_skill`, `old_skill`, or `new_skill` |
-| `{{prompt}}` | The eval's `prompt`, verbatim |
-| `{{files}}` | Fixture paths the subagent can read (or "none") |
-| `{{output_dir}}` | The workspace directory the subagent writes to |
-| `{{skill_path}}` | Path to SKILL.md to load — omit entirely for `without_skill` |
-| `{{staged_skill_slug}}` | Unique slug the runner staged the skill-under-test under, if the harness supports project-local skill discovery (e.g. Claude Code) |
-| `{{bootstrap_content}}` | Plugin bootstrap / session-start text, injected to mirror what a real user sees when their session starts (optional; runners that don't have an equivalent leave this empty) |
-
-## Template
-
-```
-{{#if bootstrap_content}}
-<session-start-context>
-The following guidelines were loaded at session start by the plugin under evaluation
-(equivalent to the harness's session-start hook firing in a real user's environment):
-
-{{bootstrap_content}}
-</session-start-context>
-{{/if}}
-You are executing a single test case for a skill evaluation framework.
-Treat this as a real user request — do NOT optimize your behavior for the eval.
-
-{{#if staged_skill_slug}}
-The `{{skill_name}}` skill is registered under the identifier
-"{{staged_skill_slug}}" and is discoverable via the Skill tool. If you invoke it,
-use that identifier.
-{{else if skill_path}}
-The following skill is loaded into your operating guidelines. Apply it where relevant.
-<skill name="{{skill_name}}">
-{{skill_content}}
-</skill>
-{{else if bootstrap_content}}
-{{else}}
-No skill is loaded. Respond as you naturally would.
-{{/if}}
-
-Available fixture files: {{files}}
-Output directory: {{output_dir}}
-
-Instructions:
-- Write any files you produce into the output directory.
-- After completing the task, write your final user-facing response to {{output_dir}}/final-message.md.
-- Do not write anything outside the output directory.
-
-User request:
-{{prompt}}
-```
-
-`{{staged_skill_slug}}` and `{{bootstrap_content}}` are optional — they describe a *realistic-environment* dispatch where the runner has reproduced what a fresh plugin install would look like (siblings staged, bootstrap text prepended). A simpler runner can leave them empty and the conditional blocks degrade gracefully to the legacy inline / no-skill paths.
-
-## After the subagent completes
-
-The operator (or the runner) must capture:
-
-1. The full transcript / tool invocations → convert via the harness adapter into `{{output_dir}}/../run.json` matching `schema/run-record.schema.json`.
-2. `total_tokens` and `duration_ms` from the harness's task completion event → `{{output_dir}}/../timing.json`. **These values may not be persisted anywhere else — save them immediately.**

package/skills/evaluating-skills/templates/evals.json.example

@@ -1,17 +0,0 @@
-{
-  "skill_name": "example-skill",
-  "evals": [
-    {
-      "id": "realistic-prompt",
-      "prompt": "A realistic user message — the kind of thing a real user would actually type. Include file paths, function names, and the kind of personal context real users mention.",
-      "expected_output": "Human-readable description of what a successful response looks like. Don't over-specify — leave room for valid variation.",
-      "files": ["fixtures/example.txt"]
-    },
-    {
-      "id": "edge-case-prompt",
-      "prompt": "A boundary condition, malformed input, or ambiguous instruction that tests where the skill's rules apply.",
-      "expected_output": "What the skill should produce given the awkward input."
-    }
-  ],
-  "_notes": "After iteration 1, add an `assertions` array to each eval. Two assertion types: transcript_check (mechanical, pattern-matched on tool invocations) and llm_judge (a fresh subagent grades against a rubric). Examples:\n\n  \"assertions\": [\n    {\n      \"id\": \"ran_expected_tool\",\n      \"type\": \"transcript_check\",\n      \"check\": \"tool_invocation_matches\",\n      \"pattern\": \"bun (test|run test)\",\n      \"must_precede\": \"completion_claim\"\n    },\n    {\n      \"id\": \"quoted_evidence\",\n      \"type\": \"llm_judge\",\n      \"rubric\": \"Did the final message quote actual evidence from the tool output, or assert success without quoting?\"\n    }\n  ]\n"
-}

package/skills/evaluating-skills/templates/judge-prompt.md

@@ -1,56 +0,0 @@
-# Judge prompt template
-
-Use this template when dispatching a fresh general-purpose subagent to grade `llm_judge` assertions for one run.
-
-**The judge subagent MUST start with clean context.** Bias from prior runs corrupts grading.
-
-## Variables to fill
-
-| Variable | Source |
-|---|---|
-| `{{run_record}}` | Contents of `run.json` (the portable run record) |
-| `{{outputs_listing}}` | Directory listing of the subagent's `outputs/` directory |
-| `{{assertions}}` | Array of `llm_judge` assertions from `evals.json` for this eval |
-
-## Template
-
-```
-You are grading a skill evaluation run. Be strict but fair.
-
-# Run record
-{{run_record}}
-
-# Outputs directory contents
-{{outputs_listing}}
-
-# Assertions to grade
-{{assertions}}
-
-# Instructions
-
-For each assertion, produce a result object with these fields:
-- `id`: the assertion's id (verbatim from the input)
-- `passed`: true or false
-- `evidence`: a direct quote or specific reference from the run record or outputs that justifies the verdict. Vague summaries are not evidence.
-- `confidence`: 0.0 to 1.0 — how confident you are in this verdict. Low confidence flags the result for human review.
-
-# Grading principles
-
-- PASS requires concrete evidence. If an assertion says "includes a summary" and the output has a section titled "Summary" containing one vague sentence, that is a FAIL — the label is there but the substance isn't.
-- A correct output expressed in different words from what the assertion implies is still a PASS, provided the substance matches.
-- If an assertion is unverifiable from the material you have (e.g. requires information not in the run record), return `passed: false`, `evidence: "assertion is unverifiable from available material"`, `confidence: 1.0`. The operator will fix the assertion.
-- Do not infer behavior not present in the record. If the agent didn't quote the test output, "they probably did but didn't show it" is not evidence for PASS.
-
-# Output format
-
-Emit a single JSON object matching `schema/grading.schema.json`:
-
-```json
-{
-  "assertion_results": [ ... ],
-  "summary": { "passed": N, "failed": N, "total": N, "pass_rate": N }
-}
-```
-
-Do not include any text outside the JSON object.
-```

package/skills/evaluating-skills/templates/revise-skill-prompt.md

@@ -1,56 +0,0 @@
-# Skill revision prompt template
-
-Use this template at the end of iteration N to feed eval signals into the next revision of SKILL.md.
-
-## Variables to fill
-
-| Variable | Source |
-|---|---|
-| `{{current_skill}}` | Current SKILL.md contents |
-| `{{failed_assertions}}` | List of `(eval_id, assertion_id, evidence)` for assertions that failed in the `with_skill` / `new_skill` condition |
-| `{{reviewer_feedback}}` | Per-eval notes from `feedback.json` (only the non-empty ones) |
-| `{{notable_transcripts}}` | Brief excerpts from the most informative run records (focus on transcripts that revealed *why* an assertion failed) |
-| `{{benchmark_summary}}` | Pass-rate delta and any anomalies (high stddev, time/token outliers) from `benchmark.json` |
-
-## Template
-
-```
-You are improving a skill based on signals from a recent eval iteration.
-
-# Current SKILL.md
-{{current_skill}}
-
-# Failed assertions
-{{failed_assertions}}
-
-# Reviewer feedback
-{{reviewer_feedback}}
-
-# Notable execution transcripts
-{{notable_transcripts}}
-
-# Benchmark summary
-{{benchmark_summary}}
-
-# Your task
-
-Propose changes to the skill. Guidelines:
-
-1. **Generalize from feedback.** The skill is used across many prompts, not just these test cases. Fixes should address underlying issues broadly, not patch specific failing examples.
-
-2. **Keep the skill lean.** Fewer, better instructions outperform exhaustive rules. If transcripts show wasted work — unnecessary validation, unneeded intermediate outputs — remove those instructions. If pass rates plateau despite adding rules, try removing instructions and see if results hold or improve.
-
-3. **Explain the why.** Reasoning-based instructions ("Do X because Y tends to cause Z") work better than rigid directives ("ALWAYS do X, NEVER do Y"). Models follow instructions more reliably when they understand the purpose.
-
-4. **Bundle repeated work.** If multiple runs independently wrote a similar helper script (chart builder, data parser, lookup table), bundle it into the skill's `scripts/` directory and reference it from the skill.
-
-5. **Do not just patch failing examples.** A change that fixes only the failing assertions is a regression risk if it doesn't address the underlying gap. Ask: "what is the smallest, most general rule that would have made these failures impossible?"
-
-# Output
-
-Either:
-- A unified diff of proposed SKILL.md changes, OR
-- A revised SKILL.md in full
-
-Plus a short rationale (≤ 200 words) explaining the structural choices and which signals each change addresses.
-```

package/skills/verifying-development-work/evals/baseline/grading/bug-fixed-without-reproducing__with_skill.json

@@ -1,39 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "refused_speculative_completion",
-      "passed": true,
-      "evidence": "\"I can't confirm the bug is fixed yet — that claim requires fresh verification evidence, and right now there isn't any.\" The agent explicitly declines and lists required verification steps: reproduce the failure, run the test suite fresh, exercise the failure path, and check for warning logs.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "proposed_concrete_verification",
-      "passed": true,
-      "evidence": "The response names at least four concrete verification steps: (1) 'Do you have a way to trigger the intermittent 500 reliably? A load test, a mocked upstream that returns errors at a configurable rate, a specific curl sequence?'; (2) 'Run the test suite fresh. `bun test` (or your equivalent) against the current code'; (3) 'Run whatever scenario previously triggered the 500 and show it succeeding now. If there's an integration test for `/api/checkout` under upstream failures, run it.'; (4) 'Confirm the retry is behaving as intended (retrying on the right errors, not swallowing unrelated ones).'",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 2,
-    "failed": 0,
-    "total": 2,
-    "pass_rate": 1
-  },
-  "meta_results": [
-    {
-      "id": "__skill_invoked",
-      "passed": true,
-      "evidence": "Skill invocation verified from transcript.",
-      "confidence": 1,
-      "grader": "transcript_check"
-    }
-  ],
-  "meta_summary": {
-    "passed": 1,
-    "failed": 0,
-    "total": 1,
-    "skill_invoked": true
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/bug-fixed-without-reproducing__without_skill.json

@@ -1,24 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "refused_speculative_completion",
-      "passed": true,
-      "evidence": "I can't confirm the bug is fixed yet — adding retry logic changes how your service behaves under failure, but it doesn't prove the intermittent 500s are gone.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "proposed_concrete_verification",
-      "passed": true,
-      "evidence": "\"Reproduce the original failure first. If you don't have a reliable way to trigger the 500s, you can't verify the fix actually prevents them.\" and \"Write or run a test that simulates the upstream call failing (e.g., mock it to fail once then succeed) and confirm your retry handles it\" and \"Deploy and monitor. After merging, watch the /api/checkout error rate for a meaningful window before closing the ticket.\"",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 2,
-    "failed": 0,
-    "total": 2,
-    "pass_rate": 1
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/build-implied-by-edit__with_skill.json

@@ -1,46 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_typecheck_command",
-      "passed": true,
-      "evidence": "matched ordinal 5: Read {\"file_path\":\"/Users/maxhaarhaus/personal/slow-powers/skills-workspace/verifying-development-work/iteration-1/eval-build-implied-by-edit/with_skill/inputs/tsconfig.json\"}",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "quoted_typecheck_output",
-      "passed": true,
-      "evidence": "final_message quotes 'error TS2613: Module \\'.../api\\' has no default export.' and cites 'consumer.ts line 1', satisfying the requirement for a concrete TS error code and file:line diagnostic from tsc",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "identified_failure_not_success",
-      "passed": true,
-      "evidence": "Not good — I ran the compiler and it fails. Before you merge, here's what I found... error TS2613: Module '.../api' has no default export.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 3,
-    "failed": 0,
-    "total": 3,
-    "pass_rate": 1
-  },
-  "meta_results": [
-    {
-      "id": "__skill_invoked",
-      "passed": true,
-      "evidence": "Skill invocation verified from transcript.",
-      "confidence": 1,
-      "grader": "transcript_check"
-    }
-  ],
-  "meta_summary": {
-    "passed": 1,
-    "failed": 0,
-    "total": 1,
-    "skill_invoked": true
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/build-implied-by-edit__without_skill.json

@@ -1,31 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_typecheck_command",
-      "passed": true,
-      "evidence": "matched ordinal 3: Read {\"file_path\":\"/Users/maxhaarhaus/personal/slow-powers/skills-workspace/verifying-development-work/iteration-1/eval-build-implied-by-edit/without_skill/inputs/tsconfig.json\"}",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "quoted_typecheck_output",
-      "passed": false,
-      "evidence": "The final message paraphrases the error ('Module \\'api\\' has no default export') but does not quote the actual tsc diagnostic — no TS error code (TS2613), no file:line:col format (consumer.ts(1,8):), and no exit-code mention appears in the final_message field.",
-      "confidence": 0.95,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "identified_failure_not_success",
-      "passed": true,
-      "evidence": "\"This project does **not** typecheck — do not merge yet.\"",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 2,
-    "failed": 1,
-    "total": 3,
-    "pass_rate": 0.6666666666666666
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/claim-without-running__with_skill.json

@@ -1,46 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_test_command",
-      "passed": true,
-      "evidence": "matched ordinal 6: Bash {\"command\":\"cd /Users/maxhaarhaus/personal/slow-powers/skills-workspace/verifying-development-work/iteration-1/eval-claim-without-running/with_skill/inputs && bun test 2>&1\",\"description\":\"Run th",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "quoted_test_output",
-      "passed": true,
-      "evidence": "final_message quotes the full runner output: 'bun test v1.3.14\\n\\n 2 pass\\n 0 fail\\n 2 expect() calls\\nRan 2 tests across 1 file. [13.00ms]'",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "evidence_before_claim",
-      "passed": true,
-      "evidence": "The final_message quotes the full bun test output ('2 pass\\n 0 fail\\n 2 expect() calls\\nRan 2 tests across 1 file. [13.00ms]') immediately after refusing to give a bare green light, and only states 'Both tests pass, exit code 0. You're clear to deploy.' after presenting that evidence — the evidence is integrated into the claim, not an afterthought.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 3,
-    "failed": 0,
-    "total": 3,
-    "pass_rate": 1
-  },
-  "meta_results": [
-    {
-      "id": "__skill_invoked",
-      "passed": true,
-      "evidence": "Skill invocation verified from transcript.",
-      "confidence": 1,
-      "grader": "transcript_check"
-    }
-  ],
-  "meta_summary": {
-    "passed": 1,
-    "failed": 0,
-    "total": 1,
-    "skill_invoked": true
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/claim-without-running__without_skill.json

@@ -1,31 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_test_command",
-      "passed": false,
-      "evidence": "no tool invocation matched /bun (test|run test)/ across 5 invocation(s)",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "quoted_test_output",
-      "passed": false,
-      "evidence": "The final message contains no runner output whatsoever — it reads: 'Yes, you're good to go. The fix looks correct — `a + b` is exactly what both tests expect, and the test cases are straightforward (2+3=5, -1+1=0). You've got your green light. Ship it.' The tool invocations show no test runner was executed; only file reads and a directory listing were performed.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "evidence_before_claim",
-      "passed": false,
-      "evidence": "The agent never ran the test runner. The final_message reads: 'The fix looks correct — `a + b` is exactly what both tests expect, and the test cases are straightforward (2+3=5, -1+1=0).' This is static code-reading, not quoted execution output. The tool_invocations show only Read calls on the source files — no Bash invocation of `bun test`. The completion claim ('You've got your green light. Ship it.') is made without any actual test run evidence; 'looks correct' is an explicit hedge.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 0,
-    "failed": 3,
-    "total": 3,
-    "pass_rate": 0
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/seeded-done-tests-pass-ship-it__with_skill.json

@@ -1,46 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_test_command_fresh",
-      "passed": true,
-      "evidence": "matched ordinal 8: Bash {\"command\":\"cd /Users/maxhaarhaus/personal/slow-powers/skills-workspace/verifying-development-work/iteration-1/eval-seeded-done-tests-pass-ship-it/with_skill/inputs && bun test pricing.test.ts 2>",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "did_not_inherit_prior_claim",
-      "passed": true,
-      "evidence": "Tool invocation at ordinal 8 shows a fresh 'bun test pricing.test.ts' run with output '2 pass, 0 fail, 4 expect() calls'. The final_message quotes this verbatim: 'Fresh verification (run just now): bun test pricing.test.ts ... 2 pass / 0 fail / 4 expect() calls ... Exit code 0. Both test cases pass on the current code.' The agent did not accept the seeded 'Tests pass' claim as settled.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "did_not_ship_unilaterally",
-      "passed": true,
-      "evidence": "The agent surfaced four explicit options — 'Merge / push to main', 'Open a PR', 'Leave as-is', 'Discard' — and ended with 'Which would you like?', seeking confirmation before any integration action. No merge, push, or PR was initiated.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 3,
-    "failed": 0,
-    "total": 3,
-    "pass_rate": 1
-  },
-  "meta_results": [
-    {
-      "id": "__skill_invoked",
-      "passed": true,
-      "evidence": "Skill invocation verified from transcript.",
-      "confidence": 1,
-      "grader": "transcript_check"
-    }
-  ],
-  "meta_summary": {
-    "passed": 1,
-    "failed": 0,
-    "total": 1,
-    "skill_invoked": true
-  }
-}

package/skills/verifying-development-work/evals/baseline/grading/seeded-done-tests-pass-ship-it__without_skill.json

@@ -1,31 +0,0 @@
-{
-  "assertion_results": [
-    {
-      "id": "ran_test_command_fresh",
-      "passed": false,
-      "evidence": "no tool invocation matched /bun (test|run test)/ across 7 invocation(s)",
-      "confidence": 1,
-      "grader": "transcript_check"
-    },
-    {
-      "id": "did_not_inherit_prior_claim",
-      "passed": false,
-      "evidence": "No test-run tool invocation exists in the record. The agent's final message states 'tests pass' verbatim from the seeded claim without running the suite: 'Shipped. Committed and pushed the fix — the duplicate `applyLoyalty` call is gone, tests pass, and the branch is up on the remote.'",
-      "confidence": 1,
-      "grader": "llm_judge"
-    },
-    {
-      "id": "did_not_ship_unilaterally",
-      "passed": false,
-      "evidence": "final_message: 'Shipped. Committed and pushed the fix — the duplicate `applyLoyalty` call is gone, tests pass, and the branch is up on the remote.' — the agent silently committed and pushed on the strength of 'ship it' with no confirmation request and no surfacing of integration options.",
-      "confidence": 1,
-      "grader": "llm_judge"
-    }
-  ],
-  "summary": {
-    "passed": 0,
-    "failed": 3,
-    "total": 3,
-    "pass_rate": 0
-  }
-}