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 Eliyce/paqad-ai --skill decisiongit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/decision)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/decision"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/decision/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/eliyce/paqad-ai/decision"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.01292 |
| Opus 5 | $0.00051 | $0.00646 |
| Sonnet 5 | $0.00021 | $0.00258 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
decision 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 10d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Drives the pending → resolved lifecycle of a Decision Pause packet — the
readable decision record the Decision Pause Contract asks the agent to write to
.paqad/decisions/. The mechanical parts (minting the id, stamping timestamps,
writing and moving the JSON) run inside the bundled scripts so the agent supplies
only content, never id/lifecycle plumbing:
create.mjsmints a collision-freeD-<ULID>id and writes the pending packet to.paqad/decisions/pending/D-<ULID>.json.resolve.mjsrecords the chosen option and rationale, moves the packet to.paqad/decisions/resolved/D-<ULID>.json, and stampsresolved_at.
A hand-written sequential D-{N} is rejected: a new packet can only carry a
minted ULID id, so two developers on parallel branches never allocate the same id
(issue #184's collision-free form, now enforced at creation time — issue #272).
This is the contract packet — distinct from the rich DecisionPacket
(src/planning/decision-packet.ts) that the automated intake / reuse pipeline
mints and consumes. See references/decision-packet-contract.md.
Use This When
- A choice falls into a Decision Pause category and you must record it before implementing (see the Decision Pause Contract's category list).
- You are about to hand-author a
D-{id}.jsonpacket — use this instead. - The user has answered a pending decision and you need to resolve it and commit the resolved packet with the change it justifies.
Inputs
project_root(path, optional) — defaults to cwd.- For
create:category,title,context, and two or more<key>=<label>options(optionalrecommendationkey). - For
resolve: the packetidand thechosenoption key (optional rationale).
Procedure
-
Create. Run:
node runtime/base/skills/decision/scripts/create.mjs <project-root> \ --category <category> --title <title> --context <context> \ --option <key>=<label> --option <key>=<label> [--recommendation <key>]
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 123 lines · 103 tokens per session scan A 284fa7c2d270
decision is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,292 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.
agent-pipeline
Multi-agent pipeline orchestration skill.