decisions

A command that records architectural decisions, proposals, comparisons, and trade-offs discussed during a coding session.

In plain words
What is it for?
It helps create a session summary of chosen approaches, deferred ideas, and the reasons behind technical decisions.
Why use it?
It prevents important reasoning from being lost, including decisions that were considered but not implemented.

Command

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 commands/scarrillo/release/decisions
Clone the repo
git clone --depth 1 https://github.com/scarrillo/release
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 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 $0.00007 $0.00674
Opus 5 $0.00003 $0.00337
Sonnet 5 $0.00001 $0.00135
Haiku 4.5 $0.00001 $0.00067

Measured yesterday against content hash 9077593d7273, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decisions 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 yesterday.

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.

commands/decisions.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decisions Document Generator

Capture decisions and proposals from the current session for future reference. Includes both implemented decisions and proposals still under consideration.

Model: Uses the model configured in release-plugin.model (see /release:changelog for model selection).

How to Run

  • Standalone: Run /decisions directly at any point to capture decisions from the current session
  • From /release:changelog: After generating a changelog, you'll be prompted to run this command

When to Use

  • After discussing architectural approaches
  • When a decision was made (implemented or not)
  • When proposals were explored but deferred
  • After comparing solutions or libraries
  • When trade-offs were evaluated
  • After a research or exploration session (even without code changes)

Instructions

  1. Review current session for:

    • Decisions made (with rationale)
    • Proposals discussed (implemented or not)
    • Approaches compared
    • Trade-offs evaluated
    • Ideas deferred for later
  2. Capture regardless of implementation status:

    • Implemented → document the decision and link to changelog
    • Not implemented → document as proposal for future review
    • Rejected → document why it was rejected (valuable context)
  3. Organize by topic for easy future reference

Output Location

If decisions.md doesn't exist, ask the user: "Where should I create the decisions document?"

  1. Project root (./decisions.md)
  2. Documentation folder (./docs/decisions.md)
  3. Same location as changelog (if it exists)
  4. Custom location (let user specify)

If decisions.md already exists, use its current location.

If file exists: Prepend new entries after the # Decisions & Proposals header (newest entries at top). Read existing content first to avoid duplicates.

Output Format

Structure:

# Decisions & Proposals

## [Topic/Feature Area] - YYYY-MM-DD

### Status: [Implemented | Proposed | Rejected | Deferred]

### Context
[What problem or question prompted this decision/proposal?]

### Proposal
[What was proposed or decided?]

### Options Considered
1. **[Option A]**: [Brief description]
   - Pros: [advantages]
   - Cons: [disadvantages]

2. **[Option B]**: [Brief description]
   - Pros: [advantages]
   - Cons: [disadvantages]

### Decision
[What was decided, or "Pending review" if still a proposal]

### Rationale
[Why this approach was chosen/proposed]

### Trade-offs Accepted
[What compromises come with this decision]

### References
- [Links to docs, samples, related PRs]

---

Read the full file on GitHub · 105 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. yesterday First seen · 105 lines · 7 tokens per session scan A 9077593d7273

Subscribe to this mod's changes

decisions is a command published in the GitHub repository scarrillo/release (9 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 674 once invoked, about $0.0000 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.