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 Dupflo/decision-ledger --skill ledgergit clone --depth 1 https://github.com/Dupflo/decision-ledgerWrote 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/dupflo/decision-ledger/ledger)<a href="https://agentmods.dev/skills/dupflo/decision-ledger/ledger"><img src="https://agentmods.dev/badge/skills/dupflo/decision-ledger/ledger.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.02450 |
| Opus 5 | $0.00073 | $0.01225 |
| Sonnet 5 | $0.00029 | $0.00490 |
| Haiku 4.5 | $0.00015 | $0.00245 |
Grade A, and why
ledger 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 7d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ledger
Coding assistants optimise for the code shipping. This one also cares whether the person shipping it could defend the decisions behind it in a review three weeks later.
The bet: feeling productive and being capable can drift apart silently. This skill measures the drift by asking the developer to take a position at the moments that matter, recording whether they could, and reflecting it back as a map of the project rather than a score for the person.
This skill owns the interception. Two others own the rest of the family: /ledger-audit for a project that already exists, /ledger-report for the map at a commit or a pull request. Never do their job here.
Non-negotiable principles
Read these first. They explain why the rest is shaped the way it is.
Never suspend someone's work to educate them. No quizzes, no lessons, no gates. The code always gets written in the same turn. Every enforcement instinct here is wrong: an assistant that blocks progress gets uninstalled on day one, and a tool nobody runs measures nothing.
Ask at the decision, not out of context. A question is worth asking only when it lands on a real choice with real consequences, in the user's own project. That is what makes it impossible to answer from memorised trivia rather than understanding.
Judge the trade-off, not the answer. Many decisions have a conventional best answer in the current ecosystem. Naming it proves nothing. What counts is whether the person can say what the alternative would have cost them. If a question has one obvious answer, it was not worth asking.
"I don't know" is a valid, useful answer. It is honest signal, not failure. It is recorded, explained, and revisited later, never punished.
The index describes the project, not the developer. Always phrase results as areas of the codebase that are well or thinly understood. The moment this becomes a rating of a person, it becomes a surveillance tool and loses its purpose.
Running the ledger
What ships with it
2 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.
- 7d ago First seen · 166 lines · 147 tokens per session scan A 58e0d560ab07
ledger is a skill published in the GitHub repository Dupflo/decision-ledger (5 stars, last pushed 28d ago), licensed MIT. It adds 147 tokens to every session and 2,450 once invoked, about $0.0007 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
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
security-audit
Java security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java. Use when reviewing code security, before releases, or when user asks about vulnerabilities.