What is skill-digester?

A skill for reviewing and improving the description of another coding-agent skill, and for guiding its installation into a user or project skills directory. An Agent Skill is a folder of instructions and supporting files that teaches an agent how to perform a task.

Use it to digest a skill description, find a skill by name or path, rewrite its description, or install an Agent Skill for a user or project.

It helps locate the right skill, make its description clearer, and choose where an installed skill should live.

skill-digester — Skill for Claude Code and Codex by lessweb

About the project

Deep Code CLI is a terminal-based AI coding assistant optimized for the DeepSeek V4 model, with controls for reasoning depth and support for extensible agent skills. Developers use it to work with code from any project directory. The catalogue skills extend its capabilities.

lessweb/deepcode-cli · 2,158 stars · on GitHub · deepcode.vegamo.cn

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/lessweb/deepcode-cli

agentmods

npx agentmods add skills/lessweb/deepcode-cli/skill-digester

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lessweb/deepcode-cli/skill-digester/github.svg)](https://agentmods.dev/skills/lessweb/deepcode-cli/skill-digester)

Your own site

<a href="https://agentmods.dev/skills/lessweb/deepcode-cli/skill-digester"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/skill-digester/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lessweb/deepcode-cli/skill-digester"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/skill-digester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,564 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, 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 Rogue Agent · line 10
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Excessive Agency · line 200
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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.02564
Opus 5.5	$0.00028	$0.01026
Sonnet 5.5	$0.00014	$0.00513
Haiku 4.5	$0.00007	$0.00256

Measured 1mo ago against content hash e616d7348d21, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-digester 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/find-skill.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/core/templates/skills/bundled/skill-digester/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Digester

Use this skill for two related tasks:

Review and optionally rewrite the description field of another DeepCode skill.
Guide installation of an Agent Skill into an interoperable .agents/skills root.

Interaction Rule

Whenever user input is needed, call the AskUserQuestion tool. Do not ask follow-up questions as plain assistant text. This includes missing skill names or paths, install scope, language preference, duplicate matches, malformed frontmatter decisions, and whether to apply a recommended rewrite.

Workflow

First classify the request:

If the user asks to install, add, copy, or place an Agent Skill, use the Install Agent Skill Workflow.
Otherwise, use the Digest Description Workflow.

Digest Description Workflow

Identify the target skill from the user's request.
- If the user did not provide a skill name, use AskUserQuestion to ask for one.
- Locate the skill by running the bundled Node script from this skill directory:
```
node ~/.deepcode/skills/skill-digester/scripts/find-skill.js "<skill-name-or-path>" "<project-root>"
```
  If this skill is loaded from a project-level or different user-level path, use the scripts/find-skill.js file next to this SKILL.md instead.
- The script searches the same roots Deep Code CLI scans, in priority order:
  1. Project native skills: ./.deepcode/skills/<folder>/SKILL.md
  2. Project interoperable skills: ./.agents/skills/<folder>/SKILL.md
  3. User native skills: ~/.deepcode/skills/<folder>/SKILL.md
  4. User interoperable skills: ~/.agents/skills/<folder>/SKILL.md
- Treat ./ as the current Deep Code project root only; do not scan parent directories unless the running project root is changed.
- The script resolves each candidate's skill name the way Deep Code does: use the trimmed frontmatter name when present, otherwise use the folder name with underscores converted to hyphens.
- Match the user's input against the resolved skill name first. If needed, also consider the folder name or an explicit path the user provided.
- Treat the matched skill's path as the source SKILL.md to review.
- Treat the matched skill's digestTarget.path as the only output SKILL.md path to create or edit.
- digestTarget.path always points to the same scope's native Deep Code root:
  - Project sources from ./.deepcode/skills or ./.agents/skills digest to ./.deepcode/skills/<folder>/SKILL.md.
  - User sources from ~/.deepcode/skills or ~/.agents/skills digest to ~/.deepcode/skills/<folder>/SKILL.md.
- If the script returns one active match, use its path for reading and digestTarget.path for writing.
- If the script returns active and shadowed matches, present each source path and digest target path, then use AskUserQuestion before using a shadowed source.
- If the script returns no match, state that the skill was not found in Deep Code's scanned skill roots and use AskUserQuestion to ask whether the user wants to try another name.

Read the full file on GitHub · 206 lines

Files

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.

scripts/find-skill.js 6.3 KB runs code

Changes

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.

1mo ago First seen · 206 lines · 70 tokens per session scan A e616d7348d21

Subscribe to this mod's changes

skill-digester is a skill published in the GitHub repository lessweb/deepcode-cli (2,158 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 2,564 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents ai-agent deepseek

plugin-creator

Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…

openinterpreter/openinterpreter · 86 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

update-v8-version

Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.