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 agentmods add skills/7xmohamed/kata/writenpx skills add 7xmohamed/Kata --skill writegit clone --depth 1 https://github.com/7xmohamed/KataWhat 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 | $0.00038 | $0.00601 |
| Opus 5 | $0.00019 | $0.00300 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
write 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 2d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write: Cut the AI Tone
Prefix your first line with ⚔️ inline, not as its own paragraph.
Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement.
Pre-flight
- Text present? If the user gave only an instruction with no actual prose to edit, ask for the text in one sentence. Do not proceed.
- Audience locked? If the intended audience is unclear and cannot be inferred from the text (blog reader vs RFC vs email), ask before editing. Junior engineer and senior architect prose should read completely different.
- Load reference: Load
references/write-en.mdbefore editing.
Read the reference file. Then edit. No summary, no commentary, no explanation of changes unless explicitly asked.
Hard Rules
- Meaning first, style second. If removing an AI pattern would change the author's intended meaning, keep the original. A failed rewrite sounds better but says something different.
- Preserve unless told to cut. Keep every sentence and paragraph unless the user explicitly asks to remove or replace specific parts. Flag unnecessary sections; do not delete them silently.
- No silent restructuring. Do not reorganize headings, reorder paragraphs, or merge sections unless structural changes are explicitly requested. Edit in place.
- Match naming conventions. Before creating new content files, check existing patterns in the target directory and follow them.
- Never guess the target text. If the request refers to "the paragraph above" or "what you just said" without quoting it, ask which exact text to edit. Do not rewrite conversation history without explicit permission.
- Stop after output. Deliver the rewritten text. Then stop. Do not append a list of changes, a justification, or a "hope this helps" closer.
- No emoji in edited text. Remove any emoji from the output unless the user explicitly asks to keep them.
Release Note Template Mode
Activate when: "release", "changelog", "version", "release notes"
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.
- 2d ago First seen · 49 lines · 38 tokens per session scan A 3f3d67205133
write is a skill published in the GitHub repository 7xmohamed/Kata (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 601 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 2026-08-31.
Other skills, from other repositories
aegisops-ai-v2
/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance and the operator should preserve the upstream workflow, copied support…
taskwing-plan
Use when you need to clarify a goal and build an approved execution plan.
taskwing-next
Use when you are ready to start the next approved TaskWing task with full context.
taskwing-done
Use when implementation is verified and you are ready to complete the current task.
aegisops-ai
/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance and the operator should preserve the upstream workflow, copied support…
taskwing-context
Use when you need project knowledge for architectural context. Returns a compact summary by default.