Borrowing it
Nothing to install: this file belongs to jakubsuplicki/codument. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jakubsuplicki/codument/main/.agents/skills/establish-charter/SKILL.mdgit clone --depth 1 https://github.com/jakubsuplicki/codumentWrote 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/jakubsuplicki/codument/establish-charter)<a href="https://agentmods.dev/skills/jakubsuplicki/codument/establish-charter"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/establish-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/jakubsuplicki/codument/establish-charter"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/establish-charter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 183 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00045 | $0.02631 |
| Opus 5 | $0.00023 | $0.01316 |
| Sonnet 5 | $0.00009 | $0.00526 |
| Haiku 4.5 | $0.00005 | $0.00263 |
Grade A, and why
establish-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 9d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Establish Charter
Use this before the normal grill loop, the first time you are about to do real building work on
a project that has no charter yet. It sets the project's seriousness and walks the user through the
core tech and architecture choices — leading with a recommendation, explaining each in plain language
with its trade-off — so even a non-technical user understands and learns the choices they make. The
result is written to docs/charter.md (summary mirrored into docs/overview.md) and biases every
later grill.
When To Run
Fire this gate when both hold:
- No
docs/charter.mdexists (the project is uncharted), and - The user's message is real-work intent — building or changing something (a feature, the app, "let's make X"), not a pure question or read-only request.
A plain question or read-only request on an uncharted project does not trip the gate: just answer it, and let the gate wait for the first real-work turn. This is a judgment call, not a string match.
Do not run it when a charter already exists — read the existing charter and proceed to the normal loop. Do not re-interview.
Core Principles
- Lead on seriousness, never on experience. The one opening question is demo/throwaway vs. serious app I intend to ship and maintain. Never ask how experienced the user is, and never branch behavior on it — that would gate a vibe coder out of the real questions and cap their learning. Everyone gets the same important questions.
- Upskilling is the goal. A non-technical user should come out understanding the choices they made, not just that choices were made.
- Infer fluency live; adapt verbosity, not the questions. Read the user's fluency from how they answer — terser when they are clearly fluent, more teaching when they ask "what's X?". Never skip a question because of inferred experience.
- Recommendation-first, one choice at a time. Never dump a questionnaire. Surface one decision, with your recommendation and why, and wait.
- Never present an unresearched guess as fact. On the serious path, when a recommendation is genuinely uncertain or best practice may have moved, research it before recommending (see Research).
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.
- 9d ago First seen · 195 lines · 45 tokens per session scan A e8786af9685a
establish-charter is a skill published in the GitHub repository jakubsuplicki/codument (47 stars, last pushed 18d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,631 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".
release-expert
Multi-repo release coordination: version alignment, RC lifecycle, release waves, rollback planning. Use when saying "release", "version alignment", or "cut an RC".
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
debug
Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".
increment
Plan a unit of work as a SpecWeave increment - spec.md with Problem, Scope, numbered ACs and an Approach, plus tasks.md. Use when starting a feature, bug, hotfix or refactor.