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 fledgeling-co/fledgeling-plugins --skill warrantgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/warrant)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/warrant"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/warrant/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/warrant"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/warrant.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 | $0.00105 | $0.02229 |
| Opus 5.5 | $0.00042 | $0.00892 |
| Sonnet 5.5 | $0.00021 | $0.00446 |
| Haiku 4.5 | $0.00011 | $0.00223 |
Grade A, and why
warrant 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warrant — the map
This plugin removes the human from per-item verification. Under it, nobody looks at an item. What survives is one standing signature on a policy file, plus whatever the owner reports when the pipeline gets something wrong.
That residual is deliberate and it is the one thing here that cannot be automated away. Four
independent research backends searched for a regulated software vendor whose all-machine
verification step had been accepted as the control of record and none found one (C21). The
obstruction is administrative. A Part 11 electronic signature, under the US Code of Federal
Regulations title 21, must be unique to one individual, and a model identifier is not an
individual (C11). And PCAOB, the US public-company audit regulator, permits leaning on last
period's testing of an automated control only where the auditor verifies the control has not
changed, which a silently reversioned model cannot satisfy (C12). Neither cuts a standing
scope with a named person answerable for it. Both cut a per-item machine verdict.
Every claim id resolves in docs/deep-research/claims.json, and references/evidence.md
separates the direct findings from the inferences.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It makes the authority answer a read of .warrant/ rather than of the ladder table, turns the forced order into a file-existence check per step, and requires all seven claim ids to resolve before any figure is quoted. Other models skip it.
The eight skills
| Skill | What it does | When to run it |
|---|---|---|
warrant:charter |
writes and validates .warrant/warrant.toml, the signed authority |
first, and at every renewal |
warrant:oracle |
lineage, tick-and-tie, taxonomy validation | before the panel plane runs |
warrant:assay |
mutation survival, cannot-fail scan, selection gap | before believing any verdict |
warrant:panel |
one out-of-family grader, orthogonal lenses, an adjudicator | per item, once the two planes above are green |
warrant:feedback |
turns a reported escape into a permanent regression case | whenever the pipeline was wrong |
warrant:lot |
risk-limited acceptance of a queue of finished items | on a backlog, or on a cadence |
warrant:ratchet |
computes earned tiers, applies revocations | after any of the above, and on a schedule |
warrant:ledger |
appends and verifies the hash-chained decision record | continuously; verified before an audit |
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 · +2 tokens per session 35d002960bc4
- 1mo ago First seen · 146 lines · 103 tokens per session scan A 861afe6ee8d7
warrant is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 2,229 once invoked, about $0.0004 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…