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 skills add jonathanmr22/pact --skill pact-initgit clone --depth 1 https://github.com/jonathanmr22/pactWrote 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/skills/jonathanmr22/pact/pact-init)<a href="https://agentmods.dev/skills/jonathanmr22/pact/pact-init"><img src="https://agentmods.dev/badge/skills/jonathanmr22/pact/pact-init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jonathanmr22/pact/pact-init"><img src="https://agentmods.dev/badge/skills/jonathanmr22/pact/pact-init.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00009 | $0.05452 |
| Opus 5.5 | $0.00004 | $0.02181 |
| Sonnet 5.5 | $0.00002 | $0.01090 |
| Haiku 4.5 | $0.00001 | $0.00545 |
Grade A, and why
pact-init 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 1mo 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before scaffolding, determine the project's scale tier and whether it delegates to a parent project.
Step 0: Project Scale
PACT has three tiers. Not every project needs 21 scaffolded files.
Tier Selection
Ask the user explicitly. Present all three tiers with descriptions and let them choose:
PACT has three scale tiers. Which fits this project?
Seed — Small utilities, scripts, CLI tools, single-purpose libraries.
Gets cognitive redirections, bug tracking, package knowledge,
and core hooks. No structural overhead.
Growth — Medium projects with databases, multiple services, or growing
complexity. Adds SYSTEM_MAP, feature flows, research system,
preflight checks, dashboard (optional), and researcher subagent.
Full — Large applications with rich UI, multiple data stores, complex
state management. Gets everything — aesthetic skill, cutting room,
capability baseline, all 3 subagents, project philosophy.
Which tier? (seed / growth / full)
You can offer context to help them decide (file count, database tables, external services), but the user chooses — don't auto-assign.
Tier Definitions
| Subsystem | Seed | Growth | Full |
|---|---|---|---|
| Cognitive redirections | ✅ | ✅ | ✅ |
| Bug tracker + solutions KB | ✅ | ✅ | ✅ |
| Package knowledge | ✅ | ✅ | ✅ |
| PENDING_WORK | ✅ | ✅ | ✅ |
| Hooks (pre-edit, post-edit, read tracker) | Core only | ✅ | ✅ |
| Preflight checks | — | ✅ | ✅ |
| SYSTEM_MAP | — | ✅ | ✅ |
| Feature flows | — | Critical paths | ✅ |
| Research knowledge base | — | ✅ | ✅ |
| Knowledge directory | — | ✅ | ✅ |
| Dashboard | — | Optional | ✅ |
| Subagents | — | Researcher only | All 3 |
| Aesthetic skill | — | — | ✅ |
| Cutting room | — | — | ✅ |
| Capability baseline | — | — | ✅ |
| Project philosophy | — | — | ✅ |
Tier guidelines (not rigid rules — the user decides):
- Seed — Small utilities, scripts, single-purpose libraries, CLI tools. <20 source files, no database, 0-1 external services. Gets the reasoning foundation without the infrastructure overhead.
- Growth — Medium projects with some complexity. 20-200 source files, a database, multiple services. Gets structural awareness (SYSTEM_MAP, flows) and research compounding.
- Full — Large applications with rich UI, multiple data stores, many integrations. 200+ source files, complex state management. Gets everything — the project's complexity justifies every subsystem.
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.
- 1mo ago First seen · 309 lines · 9 tokens per session scan A 7673402fd674
pact-init is a skill published in the GitHub repository jonathanmr22/pact (15 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 5,452 once invoked, about $0.0000 per session on Opus 5.5. 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 skills, from other repositories
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.
spec-author
Use to turn a brief into a structured product SPEC — a set of testable CLAUSES, each exactly one statement, tagged requirement / non-goal / decision — that a human edits and freezes before it feeds the decompose engine. Clarify genuine load-bearing ambiguity first, then draft, making the brief's quality requirements…
product-owner
Use to propose the next product work for a repo — on an idle factory tick (nothing ready to deliver) or when a human asks "what should we build next", for product ideas, a backlog, or PO mode. Consults Memory for product direction, inspects the repo, and files 3–5 high-leverage, anti-slop candidates into the Dispatch…
deprecate-and-remove
Use when a ticket retires something — a feature flag, an endpoint, a config option, a module, a column, a CLI command — and the removal must not break callers, data, or operators who still depend on it. Invoke for "remove the legacy X", "delete dead code", "drop the old API", or "clean up after the migration".
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.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.