pact-recall

pact-recall is a skill for Claude Code from jonathanmr22/pact. It costs 16 tokens per session (289 once invoked), scanned A, original, MIT.

A semantic search tool for finding related bugs, solutions, research, and task feedback in PACT's stored project memory.

In plain words
What is it for?
Use it to search project memory for information related to a symptom, question, or technical topic and review the closest matches.
Why use it?
It helps developers reuse earlier knowledge instead of starting an investigation from scratch.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Part of the pact plugin — 5 skills, 3 agents shipped together

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 skills/jonathanmr22/pact/pact-recall
Any agent
npx skills add jonathanmr22/pact --skill pact-recall
Clone the repo
git clone --depth 1 https://github.com/jonathanmr22/pact

Made for: Claude Code.

Or install pact, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

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-recall

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonathanmr22/pact/pact-recall.svg)](https://agentmods.dev/skills/jonathanmr22/pact/pact-recall)
Your own site
<a href="https://agentmods.dev/skills/jonathanmr22/pact/pact-recall"><img src="https://agentmods.dev/badge/skills/jonathanmr22/pact/pact-recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 289 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 5.1 $0.00016 $0.00289
Opus 5 $0.00008 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00002 $0.00029

Measured 6d ago against content hash d31d87450e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pact-recall 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 6d 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.

plugins/pact/skills/pact-recall/SKILL.md · 37 lines

What it actually says

Search the PACT vector memory for knowledge relevant to the user's query. This uses semantic similarity to find matching bugs, graduated solutions, research synthesis, and task feedback across all indexed projects.

How to use: The user provides a description of what they're looking for — a symptom, a question, a topic. You run the query and present the results.

Run this command to search:

python ~/.claude/hooks/pact-memory.py query "{user's query}" --top 5 --json

If pact-memory.py isn't at that path, check:

  • .claude/hooks/pact-memory.py (project-local)
  • The PACT templates/memory directory

Present the results to the user as:

## PACT Recall: "{query}"

Found {N} relevant results:

1. **[{score}%] [{type}] {id}**
   {text preview}
   → {file path}

2. ...

If the score is above 40%, the result is likely relevant. Below 30% is weak — mention it's a loose match.

If no results are found, suggest the user run python pact-migrate.py /path/to/project to index their knowledge files, or note that the vector index may not have been built yet.

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. 6d ago First seen · 37 lines · 16 tokens per session scan A d31d87450e38

Subscribe to this mod's changes

pact-recall is a skill published in the GitHub repository jonathanmr22/pact (15 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 289 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.

Related

Other skills, from other repositories

session-handoff

Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.

QBall-Inc/the-bulwark · 61 tokens

memory-onboard

Use this skill when the user types /memory-onboard (or asks "set up memory for this repo" / "onboard this repo to memory" / "what should be in lore for this repo?"). It runs a repo-aware onboarding interview that produces DRAFT lore records grounded in concrete repo signals (README, ADRs, recent commits, deprecation…

tmj-90/gaffer · 196 tokens

bulwark-brainstorm

Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.

QBall-Inc/the-bulwark · 50 tokens

plan-creation

Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.

QBall-Inc/the-bulwark · 38 tokens

anthropic-validator

Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.

QBall-Inc/the-bulwark · 40 tokens

code-review

Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.

QBall-Inc/the-bulwark · 61 tokens