Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsnpx agentmods add skills/fledgeling-co/fledgeling-plugins/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/fledgeling-co/fledgeling-plugins/ledger)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/ledger"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ledger/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/fledgeling-co/fledgeling-plugins/ledger"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ledger.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00087 | $0.00966 |
| Opus 5.5 | $0.00035 | $0.00386 |
| Sonnet 5.5 | $0.00017 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00097 |
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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ledger — the record that replaces the signatures
The argument for removing per-item human sign-off ends in an audit conversation, and this file is what that conversation reads. Its integrity property is the whole value: a record that can be rewritten later is a record with nothing in it.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It sets the retry ceiling on an append to zero — read the chain, then append once — turns "one row per decision" into a count read back off the ledger, and makes the run search for the repository's existing audit sink before defaulting to .warrant/ledger.jsonl. Other models skip it.
Procedure
-
Append on every decision.
python3 scripts/ledger.py --root <repo> --item <id> --class <defect-class> \ --verdict <pass|fail|inconclusive> --evidence-digest <digest> --tier <n> \ --model-id <id> --model-version <v> --warrant-version <n>Each row carries the SHA-256 hash of the previous row's canonical JSON, so a change anywhere breaks everything after it. Rows are appended and never rewritten.
-
Verify before an audit, and on a schedule.
python3 scripts/ledger_verify.py --root <repo>Exit 2 names the first broken row index and what did not match. It detects a single flipped byte in any historical row, which is the property worth testing rather than asserting.
-
Record the outcome when one emerges. An item that later turned out to be wrong gets its outcome appended as a new row referencing the original, not as an edit to it. The escape also goes to
warrant:feedback; these are two records of one event and both are wanted.
What a row has to carry
| Field | Why an auditor needs it |
|---|---|
| item | which decision this was |
| defect class | which policy covered it. warrant:ratchet counts closed items per class to decide tier 3, so a row without one cannot be counted and blocks the promotion rather than being skipped |
| warrant version | which policy authorised it |
| model id and version | which control made it, so a later change is visible (C12) |
| evidence digest | what was actually judged, so the verdict is reproducible |
| verdict | including inconclusive, which is a valid terminal answer (C13) |
| authorising tier | how much authority the class held at the time |
| outcome | whether it later proved wrong, appended rather than edited |
What ships with it
1 file 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.
- 1mo ago Changed 514bb71feb33
- 1mo ago First seen · 83 lines · 87 tokens per session scan A ced04991644e
ledger is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 966 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.