agentleFS
CodeWithJuberCodeWithJuber/forgekit/skills/forge-ledger/SKILL.md

forge-ledger

Skill2 starsChanged 4 months agoMITView on GitHub

Evidence-referenced team memory — record decisions with their evidence, query past incidents, blame a claim back to its source. Use when a decision needs a durable record, when "who decided this and why" matters, or before repeating a past mistake.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before a risky change: *did this ever bite us?* → forge ledger query.

    line 22
  2. Distinctive:

    Don't use it as a notebook for trivia.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

forge-ledger — evidence-referenced memory

Install

# from a forgekit checkout, or: npm install -g forgekit
cp -r skills/forge-ledger .claude/skills/

Requires the forge CLI on PATH.

When to use

  • Recording a decision: we chose X because of Y — with Y attached, not remembered.
  • Before a risky change: did this ever bite us? → forge ledger query.
  • "Who claimed this and on what evidence?" → forge ledger blame.
  • A claim turned out wrong → forge ledger retract (with a reason — history is append-only).
  • Human sign-off on a machine-recorded claim → forge ledger ratify.

Don't use it as a notebook for trivia. Do use it for anything a future-you (or a teammate, or an auditor) will need to trust.

Commands

forge ledger stats                    # ledger health: claims, evidence links, staleness
forge ledger query "<text>"           # find claims by content
forge ledger show <id>                # one claim with its evidence
forge ledger blame <id>               # who recorded it, when, from what source
forge ledger at <date>                # what the ledger knew on that date
forge ledger diff <since> [<until>]   # what changed between two points
forge ledger ratify <id>              # human signs off on a claim
forge ledger retract <id> --reason "<why>"   # a claim was wrong — recorded, not erased
forge ledger verify                   # re-check every claim's evidence still holds
forge ledger compact                  # distill without losing provenance
forge ledger merge <path>             # merge another ledger in
forge ledger sync [--remote <name>]   # share with the team

Append --json for machine-readable output, --personal for the personal (non-team) ledger.

The one rule

Every claim carries its evidence. A claim without a source is a rumor with a database entry. blame exists so that six months from now, someone can ask "says who?" and get an answer — a commit, a log line, a measurement — not a shrug.

See references/evidence-model.md for the claim lifecycle and references/subcommands.md for the full command reference.

References

  • references/evidence-model.md — claims, evidence, ratify/retract lifecycle
  • references/subcommands.md — every subcommand with examples

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.