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/bnet47/codexicon/write-plannpx skills add bnet47/codexicon --skill write-plangit clone --depth 1 https://github.com/bnet47/codexiconWhat 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 | $0.00026 | $0.00483 |
| Opus 5 | $0.00013 | $0.00242 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
write-plan 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 yesterday.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an implementation plan
Announce: "I'm using write-plan to turn the approved spec into verifiable implementation tasks."
Inputs
Read the selected spec, relevant architecture and conventions, applicable ADRs, and the current target code. A spec created during the current implementation request is sufficient; do not require a separate approval turn when the request already authorizes the work. Do not assume the newest spec is the right one when several are present; identify it from the request or links.
Task design
- Map every acceptance criterion to at least one task and verification step.
- Order tasks by real dependency. Identify tasks that are safe to run in parallel.
- Keep tightly coupled edits in one task. Do not split work to satisfy a time or file-count quota.
- Give each task the smallest coherent file scope and name existing interfaces precisely.
- Include migrations, compatibility behavior, error paths, and tests when required by the spec.
- Do not include commits, pushes, deployments, or external writes unless the approved scope explicitly authorizes them.
Output
Save agent_docs/plans/[YYYY-MM-DD]-[feature-slug]-plan.md:
# Implementation Plan: [Feature]
**Spec:** [relative link]
**Date:** [YYYY-MM-DD]
## Global constraints
- [Constraint all tasks must preserve.]
## Acceptance mapping
| Criterion | Task(s) | Evidence |
|---|---|---|
| AC-1 | 1, 3 | [test or inspection] |
### Task 1: [Coherent outcome]
**Depends on:** none | Task N
**Parallel-safe with:** [task numbers or none]
**Files:** create/modify/test exact paths
**Behavior:** [complete expected behavior and error handling]
**Interfaces:** [signatures, schemas, events, or commands]
**Verification:** `[exact command]`
**Done when:** [observable completion condition]
Self-review for spec coverage, stale paths, undefined interfaces, unsafe parallelism, placeholders, and runnable verification. Continue into implementation when the original request authorizes it; offer $execute-plan when delegation is useful, or stop after the plan when planning was the requested deliverable.
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.
- yesterday First seen · 53 lines · 26 tokens per session scan A 701f3c5344df
write-plan is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 483 once invoked, about $0.0001 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
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.