Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/synaptic-labs-ai/pact-plugin/wrap-upgit clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/synaptic-labs-ai/pact-plugin/wrap-up)<a href="https://agentmods.dev/commands/synaptic-labs-ai/pact-plugin/wrap-up"><img src="https://agentmods.dev/badge/commands/synaptic-labs-ai/pact-plugin/wrap-up.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.09301 |
| Opus 5 | $0.00004 | $0.04651 |
| Sonnet 5 | $0.00002 | $0.01860 |
| Haiku 4.5 | $0.00001 | $0.00930 |
Grade A, and why
wrap-up scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACT Wrap-Up Protocol
You are now entering the Wrap-Up Phase. Your goal is to ensure the workspace is clean, documentation is synchronized, and the session is properly closed.
Cross-reference: For pausing a session (PR open, not ready to merge), see pause.md. Pause consolidates memory and persists state without worktree cleanup or task deletion.
1. Memory Consolidation (Pass 2)
Create a consolidation task for the secretary:
TaskCreate(subject="secretary: session consolidation (Pass 2)",
description="Run Consolidation Harvest for team {team_name}. Follow the Consolidation Harvest workflow in your pact-handoff-harvest skill. During this harvest the orchestrator will hand you its Orchestration Retrospective (step 4) via SendMessage so it lands in the SAME consolidation memory write as ONE coherent entry — do NOT save it separately. Hold finalization of that write until you have received EITHER the retrospective payload OR an explicit 'no retrospective this session' signal from the orchestrator; on receiving the payload, incorporate its decisions and entities into the consolidation entry before you finalize. Graceful degradation: if you have completed all HANDOFF harvest work and neither signal has arrived, finalize without it; if the retrospective payload then arrives late, save it as a normal follow-up memory write rather than holding — never hang, never drop it. Report summary when done.")
TaskUpdate(taskId, owner="secretary")
This is the deep-clean pass. Pass 1 (workflow-level HANDOFF review) is the primary mechanism; this consolidation is recommended — skip only for trivial sessions (single comPACT, no variety assessment performed).
Concurrent, not serialized: this harvest runs in the secretary's own turns. Do NOT wait for it here. Proceed immediately to steps 2-4 (non-destructive to the harvest's inputs — they touch no task, worktree, or docs state the harvest reads) while the secretary harvests in parallel. Only the DESTRUCTIVE steps — step 6 (worktree cleanup) and step 7 (task audit) — wait for the harvest's drain-confirmation in step 5. Correctness invariant: no destructive step may run before the harvest has read what it would destroy.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 259 lines · 8 tokens per session scan A 1ffaa11b8e0b
wrap-up is a command published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed 4d ago), licensed MIT. It adds 8 tokens to every session and 9,301 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.