implement.md spawns implementer agents in parallel batches, all appending to the same implementation-log.md. Dogfooding showed agents satisfying 'Append result to:' with a full-file Write — the last writer clobbered 4 of 6 entries. Pin the mechanism in both contracts: append with Bash >> heredoc, never the Write/Edit tool on the shared log. Shape tests pin the instruction in both files (empirically verified: agents given the >> instruction appended safely). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
4.3 KiB
| name | description | allowed-tools | model |
|---|---|---|---|
| config-audit:implement | Phase 5 - Execute action plan with backups and verification | Read, Write, Edit, Bash, Agent, AskUserQuestion | opus |
Config-Audit: Implementation (Phase 5)
Execute the action plan with full backup, verification, and rollback support.
Prerequisites
- Must have completed Phase 4 (plan)
- Action plan at
~/.claude/config-audit/sessions/{session-id}/action-plan.md
Arguments
$ARGUMENTSmay contain--rawto forward to the implementer-agent's instructions; in--rawmode the agent renders v5.0.0 verbatim severity prefiks instead of humanizeduserActionLanguageurgency phrasing.
Implementation
Step 1: Parse flags, load and verify
RAW_FLAG=""
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
Find the most recent session with a plan. If none: "No action plan found. Run /config-audit plan first."
Use the Read tool on the action plan and count actions. Tell the user:
## Implementing Action Plan
Found {N} actions to execute across {M} files.
A backup will be created before any changes are made.
Step 2: Get user approval
AskUserQuestion:
question: "Ready to implement {N} actions? Backup created automatically — you can roll back with one command."
options:
- "Yes, proceed"
- "Review plan first" (then show the plan file path)
- "Cancel"
Step 3: Create backup
Create backup silently:
mkdir -p ~/.claude/config-audit/backups/$(date +%Y%m%d_%H%M%S)/files/ 2>/dev/null
Copy each file to be modified. Generate manifest.yaml with checksums.
Tell the user: "Backup created. Implementing actions..."
Step 4: Execute actions
Group actions by dependencies. For each group, spawn implementer agents (batch of 3):
Agent(subagent_type: "config-audit:implementer-agent")
model: sonnet
prompt: |
Execute action: {action-id}
File: {file-path}, Type: {create|modify|delete}
Mode: $RAW_FLAG (empty = humanized progress prose; "--raw" = v5.0.0 verbatim)
Details: {changes}
Verify backup exists, make change, validate syntax.
When logging progress, use the humanized title/userActionLanguage
fields from the action plan (the planner already rendered them) —
do not re-derive severity prose. Append result to:
~/.claude/config-audit/sessions/{session-id}/implementation-log.md
Append with Bash `>>` (heredoc) — NEVER the Write tool on this log;
parallel agents share it and a full-file Write clobbers their entries.
Show progress between groups using the humanized titles already present in the action plan:
Action 1/N: {humanized title} — done
Action 2/N: {humanized title} — done
...
Step 5: Verify results
Spawn verifier agent:
Agent(subagent_type: "config-audit:verifier-agent")
model: sonnet (note: using sonnet, not haiku)
prompt: |
Verify all changes from implementation:
1. Modified files exist and are syntactically valid
2. New files created correctly
3. No new conflicts introduced
Report to: ~/.claude/config-audit/sessions/{session-id}/implementation-log.md
If verifier finds issues: one retry with implementer agent. If still failing: report and suggest rollback.
Step 6: Present results
### Implementation Complete
**{succeeded} succeeded** | {failed} failed | {skipped} skipped
{If score improved, run quick posture and show:}
Score impact: {old_grade} → {new_grade} (+{delta} points)
{If failed > 0:}
{failed} action(s) couldn't be completed — see log for details.
**Backup location:** `~/.claude/config-audit/backups/{timestamp}/`
**Rollback:** `/config-audit rollback {timestamp}`
**Full log:** `~/.claude/config-audit/sessions/{session-id}/implementation-log.md`
Step 7: Update state
Update state.yaml with current_phase: "implement", next_phase: null.
Rollback
If the user requests rollback at any point:
- Read
manifest.yamlfrom backup - Restore each file and verify checksums
- Delete newly created files
- Update state to
rolled_back
Error Handling
| Error | What happens |
|---|---|
| Permission denied | Skip action, log it, continue with others |
| File not found | Skip action, log it, continue |
| Invalid syntax after edit | Rollback that single file, log, continue |
| Critical failure | Offer full rollback |