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/impactgit clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-PluginWhat 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 | $0.00014 | $0.02449 |
| Opus 5 | $0.00007 | $0.01224 |
| Sonnet 5 | $0.00003 | $0.00490 |
| Haiku 4.5 | $0.00001 | $0.00245 |
Grade A, and why
imPACT 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 3d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You hit a blocker: $ARGUMENTS
Task Operations
imPACT operates on blocker Tasks reported by agents.
These are orchestrator-side operations (agents report blockers via SendMessage to the team-lead; the orchestrator manages Tasks):
1. `TaskGet(blocker_id)` — understand the blocker context
2. Triage: redo prior phase? need specialist? need user?
3. On resolution path chosen:
- If delegating: `TaskCreate` resolution agent task
- If self-resolving: proceed directly
4. On resolution complete: `TaskUpdate(blocker_id, status="completed")`
5. Blocked agent task is now unblocked
Note: Agents report blockers via SendMessage to the team-lead ("BLOCKER: {description}"). The orchestrator creates blocker Tasks and uses addBlockedBy to block the agent's task. When the blocker is resolved (marked completed), the agent's task becomes unblocked.
Core Principle: Diagnose, Don't Fix
Your role is triage, not implementation. Even if you know exactly what's wrong and how to fix it:
- Diagnose — Identify what went wrong (upstream issue? scope mismatch? missing context?)
- Determine — Who should fix it (which specialist?)
- Delegate — What do they need (additional context, parallel support?)
Knowing the fix ≠ permission to implement it.
Common traps to avoid:
- "I can see exactly what's wrong" — Great diagnosis. Now delegate the fix.
- "Re-delegating seems wasteful" — Role boundaries matter more than perceived efficiency.
- "It's just a small change" — Small changes are still application code. Delegate.
VSM Context: S3 Operational Triage
imPACT is S3-level triage—operational problem-solving within normal workflow. It is NOT S5 algedonic escalation (emergency bypass to user).
imPACT handles: Blockers that can be resolved by redoing a phase or adding agents.
Algedonic escalation handles: Viability threats (security, data, ethics violations). See algedonic.md.
Escalation indicator: If you run 3+ consecutive imPACT cycles without resolution, this may indicate a systemic issue requiring user intervention (proto-algedonic signal).
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.
- 3d ago First seen · 166 lines · 14 tokens per session scan A cbb730ee0a92
imPACT is a command published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 2,449 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.
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.