ledger-decide

ledger-decide is a command for Claude Code from synaptiai/synapti-marketplace. It costs 12 tokens per session (1,288 once invoked), scanned A, original, Apache-2.0.

A decision-making command that turns research findings into explicit choices, with alternatives, trade-offs, supporting evidence, and recorded decisions.

In plain words
What is it for?
Use it after synthesis to review decision candidates, compare options, identify risks, filter decisions by status, and ask the user to approve each trade-off.
Why use it?
It prevents important choices from remaining vague or being made without showing what is gained and lost. It also records risks created by accepted decisions.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the context-ledger plugin — 5 skills, 8 commands, 5 agents shipped together

Good fit Use it after synthesis to review decision candidates, compare options, identify risks, filter decisions by status, and ask the user to approve each trade-off.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/synaptiai/synapti-marketplace/ledger-decide
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/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install context-ledger, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 5 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 ledger-decide

README.md
[![agentmods](https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/ledger-decide/github.svg)](https://agentmods.dev/commands/synaptiai/synapti-marketplace/ledger-decide)
Your own site
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/ledger-decide"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/ledger-decide/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.

agentmods 80×15 button for ledger-decide

Your own site · 80×15
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/ledger-decide"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/ledger-decide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,288 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 $0.00012 $0.01288
Opus 5 $0.00006 $0.00644
Sonnet 5 $0.00002 $0.00258
Haiku 4.5 $0.00001 $0.00129

Measured 10d ago against content hash ef201b4dd8df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ledger-decide 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.

plugins/context-ledger/commands/ledger-decide.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Make Decisions

Transform synthesis insights into explicit decisions with documented trade-offs.

Interactive Decision-Making: This command walks through each decision candidate, presenting options with evidence and requiring explicit user choice.

Arguments

$ARGUMENTS: Optional decision filter or focus area.

Optional flags:

  • --decisions <list> - Only process specific decision topics
  • --status <status> - Filter by decision status (accepted, provisional, rejected)
  • --risks-only - Only process risk identification (skip decisions)

Prerequisites

  • Synthesis complete (/ledger-synthesize)
  • 03-synthesis/CROSS-SYNTHESIS.md exists with decision candidates
  • Per-pillar syntheses in 03-synthesis/SYN-*.md

Workflow

  1. Load Decision Candidates

    • Extract from CROSS-SYNTHESIS.md
    • Gather supporting evidence for each
  2. For Each Decision:

    • Present options with evidence summary
    • Show trade-offs (wins/loses)
    • Request user decision via AskUserQuestion
    • Confirm trade-off acceptance
    • Record decision with semantic ID
  3. Identify Created Risks

    • For each accepted decision
    • Identify risks the decision creates
    • Document triggers and mitigations
  4. Generate Ledger Files

    • Write 04-decisions/DECISIONS.yaml
    • Write 05-risks/RISKS.yaml
  5. Validate Quality Gates

    • Decision gate: ≥2 evidence per decision
    • Risk gate: ≥1 mitigation per risk

Example Usage

Full decision process

/ledger-decide

Specific decisions only

/ledger-decide --decisions scope,pricing

Update risk mitigations

/ledger-decide --risks-only

Output

## Decisions Complete

**Decisions Made:** 8
**Status:** 6 accepted, 2 provisional
**Risks Identified:** 12

### Decisions Made
| ID | Decision | Status | Trade-offs |
|----|----------|--------|------------|
| DEC-scope-power-users-first | Target power users | accepted | +3 wins, -2 loses |
| DEC-pricing-freemium | Use freemium model | provisional | +3 wins, -3 loses |
| DEC-tech-serverless | Serverless architecture | accepted | +4 wins, -2 loses |
| ... | ... | ... | ... |

### Risks Created
| ID | Risk | Severity | Likelihood |
|----|------|----------|------------|
| RISK-retention-expert-churn | Power user churn | high | medium |
| RISK-economics-free-tier | Free tier costs | medium | medium |
| RISK-tech-cold-start | Serverless cold start | medium | low |
| ... | ... | ... | ... |

### Quality Gates
- Decision gate: ✓ All decisions cite ≥2 evidence
- Risk gate: ✓ All risks have mitigations

### Files Generated
- `04-decisions/DECISIONS.yaml`
- `05-risks/RISKS.yaml`

### Next Step
Run `/ledger-spec` to generate constrained PRD and architecture.

Read the full file on GitHub · 194 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. 10d ago First seen · 194 lines · 12 tokens per session scan A ef201b4dd8df

Subscribe to this mod's changes

ledger-decide is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 1,288 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 2026-08-31.