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/charterWrote 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/charter)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/charter"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/charter/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/charter"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/charter.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 | $0.00125 | $0.01145 |
| Opus 5.5 | $0.00050 | $0.00458 |
| Sonnet 5.5 | $0.00025 | $0.00229 |
| Haiku 4.5 | $0.00013 | $0.00114 |
Grade A, and why
charter 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Charter — the signed authority
The warrant is a file rather than a setting because of what an auditor has to be able to see.
PCAOB, the US public-company audit regulator, permits benchmarking a fully automated control
across periods only where the auditor verifies the control has not changed (C12), and a signed,
diffable, version-pinned document is the form that verification takes. DO-330, the avionics
tool-qualification standard, asks the same in tool terms: operational requirements, a
qualification plan, and re-qualification whenever the tool changes (C10).
It is also where the pipeline's single surviving human act lives. Read
references/admissibility.md before writing or renewing one.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It stops the run filling the four judgement fields the draft leaves blank, turns "Pin every lane" into a counted table with id and version per lane, and forbids raising a tier or authoring the signing commit to make validation pass. Other models skip it.
Procedure
-
Draft it from the repository, not from a conversation.
python3 scripts/charter_init.py --root <repo>It enumerates surfaces and spec files, proposes defect classes, and writes every class at tier 0. A class starts at tier 0 whatever the operator believes about it, because tiers are earned by
warrant:ratchetfrom evidence. -
Fill the four fields the script cannot infer. Each is a judgement rather than a fact about the repository, so the draft leaves them blank and
charter_validate.pyrejects the file until they are set:Key What it is owner.name,owner.emailthe person answerable for the policy. A role with no current holder is a warrant with no signature. lot.tolerable_error_raterisk appetite, in (0, 1). It sets the sample size and therefore the human time this costs.tiers.tier3_items,tiers.tier3_window_dayshow many items closed with zero escapes, over how long, earns tier 3. Too low and the ladder is decoration. staleness.dayshow old a regression run may be before classes above tier 0 lapse.
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 7bd9eda1f16a
- 1mo ago First seen · 93 lines · 125 tokens per session scan A b49d2d5ffbd0
charter is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 125 tokens to every session and 1,145 once invoked, about $0.0005 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…