comPACT

A command for sending independent coding tasks to multiple specialist agents at the same time.

In plain words
What is it for?
It helps split work such as fixing unrelated bugs, changing different endpoints, or updating separate components into concurrent subtasks.
Why use it?
It reduces waiting when separate tasks do not depend on each other or edit the same files.

Command

Install

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.

agentmods
npx agentmods add commands/synaptic-labs-ai/pact-plugin/compact
Clone the repo
git clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-Plugin
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.07196
Opus 5 $0.00007 $0.03598
Sonnet 5 $0.00003 $0.01439
Haiku 4.5 $0.00001 $0.00720

Measured 2d ago against content hash 18eab01f9b5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comPACT 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 2d 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.

pact-plugin/commands/comPACT.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatch concurrent specialists for this self-contained task: $ARGUMENTS

MANDATORY: invoke concurrently for independent sub-tasks. Sequential requires explicit file conflict or data dependency. If the task contains multiple independent items (bugs, endpoints, components), dispatch multiple specialists together — same type or mixed types — unless they share files.

⚠️ Independent ≠ same domain. "Fix CSS layout + add server logging" = 1 frontend-coder + 1 backend-coder in parallel. The key criterion is independence (no shared files, no data dependencies), not domain uniformity.


Task Hierarchy

Create a simpler Task hierarchy than full orchestrate:

1. `TaskCreate`: Feature task "{verb} {feature}" (self-contained task) — stamp metadata.variety.total (see below)
2. `TaskUpdate`: Feature task status = "in_progress"
3. Analyze: How many agents needed?
4. `TaskCreate`: Agent task(s) — direct children of feature
5. `TaskUpdate`: Agent tasks status = "in_progress"
6. `TaskUpdate`: Feature task addBlockedBy = [all agent IDs]
7. Dispatch agents concurrently with task IDs
8. Monitor via `TaskList` until all agents complete
9. `TaskUpdate`: Agent tasks status = "completed" (as each completes)
10. `TaskUpdate`: Feature task status = "completed"

Steps 8-10 are detailed in the After Specialist Completes section below (includes test verification and commit steps).

Feature-task variety stamp (step 1). Stamp the feature-level variety total on the feature TaskCreate, so the wrap-up Orchestration Retrospective can compute feature-vs-dispatch divergence instead of feature_variety_missing:

`TaskCreate(subject="{verb} {feature}", metadata={"variety": {"total": N}})`  # N = feature-level total, 4-16

Advisory, not enforced — the feature task has no teachback-gated sibling, so the dispatch-boundary gate cannot apply. The .total field is the load-bearing input compute_variety_divergence reads (the full D11 4-rationale block is fine too, but .total is the minimum). Mirrors what orchestrate.md already persists for its feature task.

Example structure:

[Feature] "Fix 3 backend bugs"           (blockedBy: agent1, agent2, agent3)
├── [Agent] "backend-coder: fix bug A"
├── [Agent] "backend-coder: fix bug B"
└── [Agent] "backend-coder: fix bug C"

Read the full file on GitHub · 467 lines

Changes

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.

  1. 2d ago First seen · 467 lines · 0 tokens per session scan A 18eab01f9b5c

Subscribe to this mod's changes

comPACT is a command published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 7,196 once invoked, about $0.0001 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.