cc-codeconductor 1.4.1 → 1.4.2

package/docs/generated/cli.md

@@ -184,6 +184,18 @@ Verify task completion with evidence.
 cc-codeconductor verify --task <id>
 ```
 
+## rdd
+
+Capture and validate Receipt-Driven Development evidence.
+
+```text
+cc-codeconductor rdd capture --task <id> [--phase red|green|review]
+cc-codeconductor rdd verify --receipt <id>
+cc-codeconductor rdd status [--task <id>]
+cc-codeconductor rdd git-check
+cc-codeconductor rdd install-hooks
+```
+
 ## seo
 
 Audit SEO and generate llms.txt.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cc-codeconductor",
-  "version": "1.4.1",
+  "version": "1.4.2",
   "description": "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
   "keywords": [
     "ai",

package/presets/agy/AGENTS.md

@@ -472,4 +472,10 @@ When the orchestrator receives a GoalGraph, it delegates tasks in dependency ord
 ### Monorepo Workspaces
 - Focus operations strictly within the specified sub-package or workspace directory in the Task Card scope. Do not modify files or run commands outside this package directory.
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->

package/presets/agy/workflows/cc-handoff.md

@@ -33,7 +33,8 @@ and wait for a human (CCEP `stopOnHighRisk`).
 Include: goal, Task Card status (no secret fields), files touched, test
 pass/fail (not log dumps), open questions, and the next `/cc-` command.
 
-Do not edit source or tests.
+Link the Delivery Ledger and verification evidence when they exist; do not
+repeat the original request or transcript. Do not edit source or tests.
 
 ---
 

package/presets/agy/workflows/cc-odd.md

@@ -0,0 +1,15 @@
+---
+description: Create or resume an opt-in Delivery Ledger for substantial authorized work.
+---
+
+# /cc-odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "$ARGUMENTS"
+bun run dev ccep resolve --command odd "$ARGUMENTS"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.

package/presets/claude/CLAUDE.md

@@ -801,4 +801,10 @@ extending capabilities, apply `.claude/skills/find-skills/SKILL.md`.
   starting.
 - Delegate verbose operations to sub-agents.
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->

package/presets/claude/commands/cc/handoff.md

@@ -35,7 +35,8 @@ recommended `context_scope` (`isolated` | `continuation` | `full`) for the next
 session — derived from the Task Card status above, not invented, with a
 one-sentence justification.
 
-Do not edit source or tests.
+Link the Delivery Ledger and verification evidence when they exist; do not
+repeat the original request or transcript. Do not edit source or tests.
 
 ---
 

package/presets/claude/commands/cc/odd.md

@@ -0,0 +1,15 @@
+---
+description: Create or resume an opt-in Delivery Ledger for substantial authorized work.
+---
+
+# /cc:odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "$ARGUMENTS"
+bun run dev ccep resolve --command odd "$ARGUMENTS"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.

package/presets/codex/AGENTS.md

@@ -1084,4 +1084,10 @@ Contract version:** v0.1.0 **Date:** [YYYY-MM-DD] **Evaluator:** [human name or
   starting.
 - Delegate verbose operations to sub-agents.
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->

package/presets/codex/skills/cc-handoff/SKILL.md

@@ -34,7 +34,9 @@ errors instead of pasting dumps. If unresolved credential material remains, stop
 and wait for a human (CCEP `stopOnHighRisk`).
 
 Include: goal, Task Card status (no secret fields), files touched, test
-pass/fail (not log dumps), open questions, and the next `$cc-` command.
+pass/fail (not log dumps), open questions, the next `$cc-` command, plus links
+to the Delivery Ledger and verification evidence when they exist. Do not repeat
+the original request or transcript.
 
 Do not edit source or tests.
 

package/presets/codex/skills/cc-odd/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: cc-odd
+description: Create or resume an opt-in Delivery Ledger for substantial authorized work.
+---
+
+# odd
+
+Invoke as `$cc-odd`. The user request follows the skill mention.
+
+# /cc:odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "$ARGUMENTS"
+bun run dev ccep resolve --command odd "$ARGUMENTS"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.
+
+When ODD has verification evidence, include its RDD receipt in the ledger
+handoff. On resume, verify it against the workspace before relying on a prior
+test or review result. If it is stale, keep the ledger and repeat only the
+invalidated verification.

package/presets/codex/skills/cc-openspec/SKILL.md

@@ -138,6 +138,10 @@ npx cc-codeconductor openspec archive <itemId>
 
 `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `archive` requires all cards done (and review evidence when Global review is required) and moves `openspec/changes/<slug>` to `archive/`.
 
+For test and implementation cards, `done` also requires a current RDD-backed
+RED or GREEN receipt respectively. Do not reuse evidence after candidate files
+change; capture and verify the matching receipt again.
+
 ---
 
 ## Step 5 — Model matrix and execute loop

package/presets/codex/skills/cc-spec-mutation/SKILL.md

@@ -131,6 +131,11 @@ Verdict is binary: PASS continues to the mutation gate; REJECT returns to the
 
 ## Stage 5 — Mutation gate (`mutation_testing`)
 
+RDD complements this gate: capture the candidate receipt before Mutation Testing
+and verify it after the runner restores production source. A survivor opens a
+new tester/reviewer-approved test revision; it never makes an earlier receipt
+valid again.
+
 Run the deterministic AST mutator shipped with this preset:
 
 ```bash

package/presets/codex/skills/cc-tdd-cycle/SKILL.md

@@ -70,6 +70,14 @@ runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
 
 Do not advance phases until that evidence exists.
 
+### Receipt-Driven Development
+
+Run the verification runner with the matching `phase` (`red`, `green`, or
+`refactor`). It records an RDD receipt for the complete candidate. Before a
+handoff, phase transition, or final review, verify that receipt. A changed
+source, test, contract, lockfile, or runner configuration invalidates it and
+requires the affected phase to run again.
+
 ---
 
 ## Phase 1 — RED (Tester role)

package/presets/cursor/AGENTS.md

@@ -459,6 +459,12 @@ docs | test **Risk:** low | medium | high **Scope:** [files or modules affected]
 **Agent:** [agent name] **Requires review:** yes | no
 ```
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->
 
 ---

package/presets/cursor/commands/cc/handoff.md

@@ -30,7 +30,9 @@ errors instead of pasting dumps. If unresolved credential material remains, stop
 and wait for a human (CCEP `stopOnHighRisk`).
 
 Include: goal, Task Card status (no secret fields), files touched, test
-pass/fail (not log dumps), open questions, and the next `/cc:` command.
+pass/fail (not log dumps), open questions, the next `/cc:` command, plus links
+to the Delivery Ledger and verification evidence when they exist. Do not repeat
+the original request or transcript.
 
 Do not edit source or tests.
 

package/presets/cursor/commands/cc/odd.md

@@ -0,0 +1,20 @@
+---
+description: Create or resume an opt-in Delivery Ledger for substantial authorized work.
+---
+
+# /cc:odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "$ARGUMENTS"
+bun run dev ccep resolve --command odd "$ARGUMENTS"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.
+
+When ODD has verification evidence, include its RDD receipt in the ledger
+handoff. On resume, verify it against the workspace before relying on a prior
+test or review result. If it is stale, keep the ledger and repeat only the
+invalidated verification.

package/presets/cursor/commands/cc/openspec.md

@@ -135,6 +135,10 @@ npx cc-codeconductor openspec archive <itemId>
 
 `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `archive` requires all cards done (and review evidence when Global review is required) and moves `openspec/changes/<slug>` to `archive/`.
 
+For test and implementation cards, `done` also requires a current RDD-backed
+RED or GREEN receipt respectively. Do not reuse evidence after candidate files
+change; capture and verify the matching receipt again.
+
 ---
 
 ## Step 5 — Model matrix and execute loop

package/presets/cursor/commands/cc/spec-mutation.md

@@ -129,6 +129,11 @@ Verdict is binary: PASS continues to the mutation gate; REJECT returns to the
 
 ## Stage 5 — Mutation gate (`mutation_testing`)
 
+RDD complements this gate: capture the candidate receipt before Mutation Testing
+and verify it after the runner restores production source. A survivor opens a
+new tester/reviewer-approved test revision; it never makes an earlier receipt
+valid again.
+
 Run the deterministic AST mutator shipped with this preset:
 
 ```bash

package/presets/cursor/commands/cc/tdd-cycle.md

@@ -68,6 +68,14 @@ runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
 
 Do not advance phases until that evidence exists.
 
+### Receipt-Driven Development
+
+Run the verification runner with the matching `phase` (`red`, `green`, or
+`refactor`). It records an RDD receipt for the complete candidate. Before a
+handoff, phase transition, or final review, verify that receipt. A changed
+source, test, contract, lockfile, or runner configuration invalidates it and
+requires the affected phase to run again.
+
 ---
 
 ## Phase 1 — RED (Tester role)

package/presets/gemini/GEMINI.md

@@ -35,4 +35,10 @@ intent to the right slash command.
 - Do not skip the Reviewer step for medium- or high-risk changes.
 - Do not store secrets in any file loaded by Gemini CLI.
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->

package/presets/gemini/commands/cc/handoff.toml

@@ -28,7 +28,9 @@ errors instead of pasting dumps. If unresolved credential material remains, stop
 and wait for a human (CCEP `stopOnHighRisk`).
 
 Include: goal, Task Card status (no secret fields), files touched, test
-pass/fail (not log dumps), open questions, and the next `/cc:` command.
+pass/fail (not log dumps), open questions, the next `/cc:` command, plus links
+to the Delivery Ledger and verification evidence when they exist. Do not repeat
+the original request or transcript.
 
 Do not edit source or tests.
 

package/presets/gemini/commands/cc/odd.toml

@@ -0,0 +1,20 @@
+description = "Create or resume an opt-in Delivery Ledger for substantial authorized work."
+
+prompt = """
+# /cc:odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "{{args}}"
+bun run dev ccep resolve --command odd "{{args}}"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.
+
+When ODD has verification evidence, include its RDD receipt in the ledger
+handoff. On resume, verify it against the workspace before relying on a prior
+test or review result. If it is stale, keep the ledger and repeat only the
+invalidated verification.
+"""

package/presets/gemini/commands/cc/openspec.toml

@@ -132,6 +132,10 @@ npx cc-codeconductor openspec archive <itemId>
 
 `start` moves the card `pending → doing` and the item `PLANNED → IN_PROGRESS`. `done` marks the card complete, updates Progress, and moves the item to `REVIEW` when every card is done and review is required. `archive` requires all cards done (and review evidence when Global review is required) and moves `openspec/changes/<slug>` to `archive/`.
 
+For test and implementation cards, `done` also requires a current RDD-backed
+RED or GREEN receipt respectively. Do not reuse evidence after candidate files
+change; capture and verify the matching receipt again.
+
 ---
 
 ## Step 5 — Model matrix and execute loop

package/presets/gemini/commands/cc/spec-mutation.toml

@@ -125,6 +125,11 @@ Verdict is binary: PASS continues to the mutation gate; REJECT returns to the
 
 ## Stage 5 — Mutation gate (`mutation_testing`)
 
+RDD complements this gate: capture the candidate receipt before Mutation Testing
+and verify it after the runner restores production source. A survivor opens a
+new tester/reviewer-approved test revision; it never makes an earlier receipt
+valid again.
+
 Run the deterministic AST mutator shipped with this preset:
 
 ```bash

package/presets/gemini/commands/cc/tdd-cycle.toml

@@ -64,6 +64,14 @@ runner) — do not hand-edit JSON under `.codeconductor/evidence/`.
 
 Do not advance phases until that evidence exists.
 
+### Receipt-Driven Development
+
+Run the verification runner with the matching `phase` (`red`, `green`, or
+`refactor`). It records an RDD receipt for the complete candidate. Before a
+handoff, phase transition, or final review, verify that receipt. A changed
+source, test, contract, lockfile, or runner configuration invalidates it and
+requires the affected phase to run again.
+
 ---
 
 ## Phase 1 — RED (Tester role)

package/presets/opencode/agents/implementer.md

@@ -222,3 +222,5 @@ Invoke via `/cc-feature`, `/cc-fix`, `/cc-tdd-cycle`, or the orchestrator.
 Do not invoke other agents. Invoke skill `testing-tdd`.
 Deliverable is incomplete without a passing suite and runner TDD evidence when
 TDD is required. Scorecard: `bun run dev scorecard create --from-diff`.
+Before handing work to review or delivery, verify the current RDD receipt. Do
+not rely on a test result if its candidate has changed.

package/presets/opencode/agents/reviewer.md

@@ -288,3 +288,5 @@ Invoke skill `evaluation` and run `scorecard record` with agent `reviewer`, mode
 Invoke via `/cc-review` or the orchestrator. Do not invoke other agents.
 Invoke skill `evaluation`. Deliverable is incomplete without
 `scorecard create --from-diff` and a recorded PASS|REVISE|REJECT.
+An approval applies only to the RDD candidate receipt supplied with the review;
+request a fresh verification when it is stale.

package/presets/opencode/agents/tester.md

@@ -291,3 +291,5 @@ and confirmed failing; list the failing test paths in `artifacts` so the
 Invoke via `/cc-tdd-cycle`, `/cc-feature`, or the orchestrator (test before
 implement). Do not invoke other agents. Invoke skill `testing-tdd`.
 Deliverable is incomplete without `captureTddSuiteEvidence` when TDD is required.
+Record the matching RDD receipt and report it with the test evidence. A changed
+candidate requires a new verification before handoff.

package/presets/opencode/commands/cc-handoff.md

@@ -31,7 +31,8 @@ and wait for a human (CCEP `stopOnHighRisk`).
 Include: goal, Task Card status (no secret fields), files touched, test
 pass/fail (not log dumps), open questions, and the next `/cc-` command.
 
-Do not edit source or tests.
+Link the Delivery Ledger and verification evidence when they exist; do not
+repeat the original request or transcript. Do not edit source or tests.
 
 ---
 

package/presets/opencode/commands/cc-odd.md

@@ -0,0 +1,15 @@
+---
+description: Create or resume an opt-in Delivery Ledger for substantial authorized work.
+---
+
+# /cc-odd
+
+## Step 0 — CCEP Bootstrap
+
+```bash
+bun run dev ccep parse --command odd "$ARGUMENTS"
+bun run dev ccep resolve --command odd "$ARGUMENTS"
+bun run dev ccep profile --command odd
+```
+
+Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.

package/presets/pi/AGENTS.md

@@ -40,4 +40,10 @@ act as that role for the rest of the step.
 - Do not skip the Reviewer step for medium- or high-risk changes.
 - Do not store secrets in any file loaded by Pi.
 
+## Receipt integrity
+
+- For any implementation, test, review, handoff, or delivery decision, capture or verify the current RDD receipt with `bun run dev rdd`.
+- A receipt is valid only for its exact candidate. If code, tests, contracts, or runner configuration changed, repeat the affected verification.
+- TDD and Mutation Testing retain their existing gates; RDD verifies that their observed evidence still belongs to the current candidate.
+
 <!-- CODECONDUCTOR:END managed -->

package/src/presets/targets/pi.yml

@@ -2,6 +2,7 @@ target: pi
 invocation: hyphen
 commandFormat: markdown
 contextFile: AGENTS.md
+# ODD is available through `bun run dev odd`; Pi installs no slash-prompt files.
 # No Task tool or subagents (deliberate design choice, per pi's own docs) —
 # same style as opencode and agy, which share the reason.
 subagentInvocationStyle: invoke-with-context