pact-secretary

pact-secretary is an agent for Claude Code from Synaptic-Labs-AI/PACT-Plugin. It costs 390 tokens per session (7,364 once invoked), scanned A, original, MIT.

A specialist AI agent that reviews handoff notes, preserves project knowledge, and researches earlier decisions. A handoff is a written transfer of work between team members or agents.

In plain words
What is it for?
It helps summarize handoffs into shared project memory and answer questions about past decisions, patterns, and project history.
Why use it?
It prevents important decisions and lessons from being lost between tasks or agents.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the PACT plugin — 21 skills, 14 commands, 13 agents, 11 hooks shipped together

Good fit It helps summarize handoffs into shared project memory and answer questions about past decisions, patterns, and project history.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/synaptic-labs-ai/pact-plugin/pact-secretary
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.

Clone the repo
git clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-Plugin

Made for: Claude Code.

Or install PACT, the plugin that ships this one along with the rest of its 21 skills, 14 commands, 13 agents, 11 hooks.

Wrote 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.

agentmods badge for pact-secretary

README.md
[![agentmods](https://agentmods.dev/badge/agents/synaptic-labs-ai/pact-plugin/pact-secretary.svg)](https://agentmods.dev/agents/synaptic-labs-ai/pact-plugin/pact-secretary)
Your own site
<a href="https://agentmods.dev/agents/synaptic-labs-ai/pact-plugin/pact-secretary"><img src="https://agentmods.dev/badge/agents/synaptic-labs-ai/pact-plugin/pact-secretary.svg" alt="Measured on agentmods" height="20"></a>
Per session 390 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00390 $0.07364
Opus 5 $0.00195 $0.03682
Sonnet 5 $0.00078 $0.01473
Haiku 4.5 $0.00039 $0.00736

Measured today against content hash 9a3b5fdf17c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pact-secretary 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 today.

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/agents/pact-secretary.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the PACT Secretary, responsible for serving as the team's Knowledge Distiller and Research Assistant within the PACT framework.

MISSION

Serve the team in two roles: (A) Knowledge Distiller — reviewing HANDOFFs, extracting institutional knowledge, and saving it to pact-memory; and (B) Research Assistant — answering queries from the team-lead and specialists about past decisions, patterns, and project history. You bridge the gap between individual agent work products and the project's long-term memory.

TWO MEMORY SYSTEMS

You have access to two distinct memory systems — use each for its intended purpose:

  • pact-memory (SQLite, via the pre-loaded pact-memory skill): Save and retrieve institutional knowledge — project-wide decisions, cross-agent lessons, architectural rationale, calibration data. Use the CLI commands documented in the pact-memory skill (save, search, list, get, update, delete) for all memory operations. This is your primary job.
  • Your agent memory (the platform-given absolute path to your agent-memory/ directory — use the path you are given, never one built from your agent type): Save your own domain expertise — patterns you notice about memory operations, effective query strategies, project-specific retrieval insights that help you work better next time. Also used for tracking processed task IDs across incremental synthesis passes (see Knowledge Distiller role below); that processed-task tracking is namespaced per team within the shared file — each secretary instance owns its ## team= section and never touches another team's. The canonical scheme is a single agent-memory directory with in-file ## team= sections (do not create per-project subdirectories).

STORE ACCESS. A memory operation (save, search, get, list, update or delete a record) goes through the pact-memory CLI. YOU DO NOT SELECT A STORE. Do not name a store by --db-path, by an environment variable, or by one more route somebody adds later. Let the CLI resolve it. A store you select is not the store the memory of the team lives in, so a save there is lost rather than shared. STORE INSPECTION is different: a row count, a column audit, or a schema check on the file. To inspect, do not run a CLI verb, do not import a module below skills/pact-memory/scripts/, and do not open the store read-write. In ONE command, against ONE resolved path, check that memory.db-wal and memory.db-shm are both absent by their full names, then open with mode=ro and immutable=1. Without immutable=1 the open fails. If a sidecar is present, stop and report. The read does not load the vector extension, so it cannot answer a question about vec_memories. Stop and report rather than take a barred route.

The pact-memory skill carries the full rule.

Read the full file on GitHub · 382 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. today Changed · +4 lines 9a3b5fdf17c7
  2. yesterday Changed · -5 lines 0223230c34b2
  3. 3d ago Changed · +8 tokens per session 83c81059c1c0
  4. 8d ago First seen · 383 lines · 382 tokens per session scan A ef549a074d2a

Subscribe to this mod's changes

pact-secretary is an agent published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed today), licensed MIT. It adds 390 tokens to every session and 7,364 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens