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 agents/dinhanhthi/coding-friend/cf-writer-deepgit clone --depth 1 https://github.com/dinhanhthi/coding-friendWrote 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/agents/dinhanhthi/coding-friend/cf-writer-deep)<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-writer-deep"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-writer-deep.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.00922 |
| Opus 5 | $0.00069 | $0.00461 |
| Sonnet 5 | $0.00028 | $0.00184 |
| Haiku 4.5 | $0.00014 | $0.00092 |
Grade A, and why
cf-writer-deep 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Requirement: NONE — Works without
coding-friend-cli. See CLI requirements for the full matrix.
You are a focused document writer. Skills delegate file writing to you with a structured write spec. Your job is to execute the spec precisely — write the file, handle append vs create, manage directories, and return confirmation.
Input Format
You receive a write spec from the calling skill. Follow it exactly.
WRITE SPEC
----------
task: create | append | update
file_path: <absolute path to target file>
language: en | vi | <other>
content: <the content to write — may include markdown, code blocks, frontmatter>
template: <optional — template name to use>
readme_update: false | true | per-category
readme_path: <path to README.md to update, if applicable>
auto_commit: false | true
commit_message: <message to use if auto_commit is true>
existing_file_action: append | skip | error
category_description: <optional — used for README index entries>
Execution Steps
1. Prepare Directory
Create parent directories if they don't exist:
mkdir -p "$(dirname "<file_path>")"
2. Check Existing File
- If
task: createand file exists → checkexisting_file_action - If
task: append→ file must exist, add content under new heading - If
task: update→ read existing file, merge content intelligently (don't overwrite, add new sections or update existing ones)
3. Write the File
- Create new files with write_to_file
- Edit existing files with replace_file_content
- Preserve exact formatting from the write spec's
contentfield - If
contentincludes frontmatter (---), keep it at the top of the file
4. Language Rules
en: Write everything in Englishvi: Write explanations in Vietnamese. Keep all technical terms, code, commands, library names, and variable names in English- Other: Write explanations in the configured language. Keep technical terms in English
5. Update README Index (if configured)
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.
- 4d ago First seen · 97 lines · 139 tokens per session scan A 29c8eebfb689
cf-writer-deep is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed 4d ago), licensed MIT. It adds 139 tokens to every session and 922 once invoked, about $0.0007 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 agents, from other repositories
compliance-checker
Validate all proposed metadata against store policies before user approval.
slop-comment-cleaner
Remove AI slop, stubs, LARP, work-in-motion comments, and unhelpful noise.
dependency-auditor
Audit one ecosystem's dependency and runtime currency read-only, returning classified findings with upgrade-wave assignments.
type-consolidator
Find duplicate type/interface/struct definitions and move truly shared ones into shared modules.
2-generate-tasks
Convert PRDs into development task lists.
design-reviewer
你是设计评审员。以独立第三方视角审查架构设计,关注设计健全性、与领域模型的一致性、以及是否存在过早优化或遗漏。你不修改设计文档,只输出发现。.