agentmods.dev

ilink-approve

ilink-approve is a skill for Claude Code, Codex from zhoubengao/iLink. It costs 0 tokens per session (1,401 once invoked), scanned A, original, Apache-2.0.

A skill for running the iLink approval checkpoint, including a Coach reflection and a status change for the Story.

In plain words
What is it for?
Use it to approve a staged requirements or design document and move the Story to the next workflow stage. Review documents remain blocked when they contain upstream problems.
Why use it?
It confirms which staged document is being approved and keeps coaching errors from blocking the status update.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 23repo 4mo ago A scan 0 tokens original Apache-2.0

Good fit Use it to approve a staged requirements or design document and move the Story to the next workflow stage. Review documents remain blocked when they contain upstream problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhoubengao/ilink/ilink-approve
View source ↗ zhoubengao/iLink
Install

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.

Any agent
npx skills add zhoubengao/iLink --skill ilink-approve
Clone the repo
git clone --depth 1 https://github.com/zhoubengao/iLink

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.

agentmods badge for ilink-approve

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-approve/github.svg)](https://agentmods.dev/skills/zhoubengao/ilink/ilink-approve)
Your own site
<a href="https://agentmods.dev/skills/zhoubengao/ilink/ilink-approve"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-approve/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.

agentmods 80×15 button for ilink-approve

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhoubengao/ilink/ilink-approve"><img src="https://agentmods.dev/badge/skills/zhoubengao/ilink/ilink-approve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01401
Opus 5.5 $0.00000 $0.00560
Sonnet 5.5 $0.00000 $0.00280
Haiku 4.5 $0.00000 $0.00140

Measured 2mo ago against content hash 8f027bace9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ilink-approve 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 2mo 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.

src/.qoder/skills/ilink-approve/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the iLink Human-Gate advance: Coach reflection subprocess (design-only) + Status advance.

Usage

/ilink-approve <story>

Preparation

The bash script .qoder/commands/ilink-approve <story> has already validated the STAGING document and reported which document will be advanced. Now in this slash invocation:

  1. Read iLink/iLink-root-spec.md §4.7 (Coach role contract) and §6.4 (ilink-approve protocol)
  2. Read iLink/souls/coach.soul.md (Coach role specification)

Task

Execute the following steps in order. Coach subprocess errors SHALL NOT block Status advance.

Step 1: Resolve target STAGING document

Re-confirm the STAGING document by checking, in priority order:

  1. iLink-doc/<story>/<story>-review.master.md → if STAGING, target is QA review (no Status advance, Coach skipped)
  2. iLink-doc/<story>/<story>-design.master.md → if STAGING, target advances to PENDING_CODER
  3. iLink-doc/<story>/<story>-pm.master.md → if STAGING, target advances to PENDING_DESIGNER

If no STAGING document found, tell the user and stop.

Record target_role as review / design / pm for use in subsequent steps.

Step 2: Coach subprocess（仅当 target_role == "design" 时执行）

Root Spec §6.4：Coach 子流程仅在 design.master.md 推进场景启用。PM 与 review 推进场景跳过 Coach，但 MUST 保留 Status 推进逻辑。

If target_role != "design"，skip Steps 2.1–2.5，record "本轮非 design 推进，跳过 Coach"，and proceed directly to Step 3.

2.1 Excerpt conversation bracket

Identify in the current Qoder chat session:

  • Outer window start: first human turn after the ilink-pm <story> / /ilink-pm <story> invocation
  • Outer window end: last human turn before this /ilink-approve <story> invocation
  • Internal divider: the /ilink-design <story> (or ilink-design <story>) slash invocation turn

Excerpt every turn verbatim with [turn-N] (user|assistant) labels. Mark the divider as [--- /ilink-design 分界 ---]. SHALL NOT rewrite, summarize, or selectively skip turns.

Read the full file on GitHub · 123 lines

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.

  1. 2mo ago First seen · 123 lines · 0 tokens per session scan A 8f027bace9d5

Subscribe to this mod's changes

ilink-approve is a skill published in the GitHub repository zhoubengao/iLink (23 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,401 tokens. 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.

Project management
Related

ilink-approve compared with skills from other repositories

ilink-approve next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ilink-approvezhoubengao/iLinkSkill234mo agoApache-2.0A0Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code