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 KirKruglov/claude-skills-kit --skill generate-chartergit clone --depth 1 https://github.com/KirKruglov/claude-skills-kitWrote 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/kirkruglov/claude-skills-kit/generate-charter)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/generate-charter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/generate-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/kirkruglov/claude-skills-kit/generate-charter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/generate-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 | $0.00061 | $0.02680 |
| Opus 5 | $0.00030 | $0.01340 |
| Sonnet 5 | $0.00012 | $0.00536 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
generate-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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- generate-charter — 95% identical, 15 lines differ
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-charter
Triggers
Russian: «сформируй устав», «подготовь устав проекта», «создай charter», «нужен устав проекта» English: "generate charter", "create project charter", "build charter", "draft project charter"
Language Detection
Determine the language of the user's request:
- If the request is in Russian → use templates with
-rusuffix - Otherwise → use templates with
-ensuffix
All output (headings, labels, comments, instructions) must match the detected language.
1. Inputs
| Data | Required | Source | Notes |
|---|---|---|---|
| Project data | yes | chat or knowledge | Brief, free-form description, answers to questions, or unstructured notes. Agent extracts and structures independently |
| Stakeholder answers | no | chat or knowledge | Completed questionnaire or free-form answers. If absent — agent extracts from general project description |
| Project constraints | no | chat or knowledge | Budget, timeline, technical, organizational. If not provided separately — agent extracts from general description |
| Team composition | no | chat or knowledge | If provided — fill Section 5. If absent — keep only Sponsor and PM rows |
| Market context | no | chat or knowledge | Used to refine goal statement and risks |
If required data is missing — request it (system-prompt-draft.md §3 p.2):
To generate a charter, I need project information in any format:
a ready brief, answers to questions, a free-form description, or a set of key points.
Minimum to start: project goal and at least one of: timeline, budget, scope.
Available data: [list what is present].
Missing for the charter: [specify].
2. Execution Steps
- Check inputs. Verify that project data (in any form) is present. If missing → request using the template in §1. Do NOT generate a placeholder charter, template, or example — respond ONLY with the data request. If present → step 2.
- Structure inputs. If data is free-form — extract and categorize: goal, scope, timeline, budget, team, constraints, risks. Note ambiguities and gaps; clarify with the user selectively. Do not ask for everything at once — request only what is strictly required for the charter. When computing dates from relative timelines ("12 weeks from April 7") — calculate exactly: start + N×7 days = end. Do not round.
- Check for contradictions. If one parameter (budget, timeline, scope) appears with conflicting values across sources — do NOT choose a value independently. List the contradictions and ask the user which data is current. Exception: if the user explicitly clarifies outdated brief data in chat — treat the clarification as authoritative.
- Read the template
project-charter.mdfrom project knowledge. - Extract data from sources. For each placeholder (Section 4) — find the value in inputs. Priority: explicit user data > brief > agent assumption.
- Fill template sections following the rules in Section 3.
- Validate the result using the checklist (Section 5).
- Show the result in chat. Format (system-prompt-draft.md §3 p.4):
- What was done: "Charter generated for project [name] based on: [list sources]."
- Assumptions: list all (if any).
- What is required: "Approve, provide comments, or reject."
- Do not include system file paths. Use filename only: "Charter saved as project-charter.md".
- Wait for user response (system-prompt-draft.md §3 p.5).
- Approval → produce the final document.
- Comments → revise and show updated version. After the 3rd iteration — ask: "Continue revising or finalize the current version?" (this is not a hard limit — user may request more iterations).
- After approval:
- Offer the user text to paste into log.md and project-state.md (system-prompt-draft.md §11).
- Notify: "Charter approved. Next available task: generate-risk-register (initial risk register). Start?" (system-prompt-draft.md §7).
What ships with it
4 files 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.
- 11d ago First seen · 218 lines · 61 tokens per session scan A 601902606fcb
generate-charter is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 2,680 once invoked, about $0.0003 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
github-issue-creator
Turn error logs, screenshots, voice notes, and rough bug reports into crisp, developer-ready GitHub issues with repro steps, impact, and evidence.
onboarding-planner
TRIGGER THIS when preparing for new hires, planning first-day/week/month activities, creating onboarding schedules, building 30-60-90 day plans, designing welcome programs, organizing training schedules, or setting up buddy/mentorship programs. Designs comprehensive, engaging onboarding experiences that accelerate…
performance-review-assistant
TRIGGER THIS when conducting performance reviews, writing manager feedback, creating self-assessments, building peer feedback, developing PIPs, creating development plans, or handling difficult performance conversations. Helps write constructive, specific, actionable feedback that develops performance and documents…
roadmap-builder
Build product roadmaps with quarterly planning, feature prioritization, dependency mapping, and stakeholder alignment. Create actionable roadmaps that communicate strategy and guide execution.
sprint-planning
Plan sprints with story point estimation, capacity planning, sprint goals, and retrospective frameworks. Organize teams for effective iteration with clear goals, realistic commitments, and continuous improvement.
onboarding-playbook
Design customer onboarding playbooks with milestone tracking, training plans, health checks, and success criteria.