symlink-checker

symlink-checker is an agent for coding agents from yacb2/aidex. It costs 20 tokens per session (829 once invoked), scanned A, original, MIT.

An agent that checks whether symbolic links in a project's and user's .claude folders point to existing targets.

In plain words
What is it for?
Use it to scan project and global skills, commands, and rules directories and report invalid symbolic links.
Why use it?
It catches broken links that can prevent skills, commands, or rules from being found or used.

Agent

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.

agentmods
npx agentmods add agents/yacb2/aidex/symlink-checker
Clone the repo
git clone --depth 1 https://github.com/yacb2/aidex

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 symlink-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/yacb2/aidex/symlink-checker.svg)](https://agentmods.dev/agents/yacb2/aidex/symlink-checker)
Your own site
<a href="https://agentmods.dev/agents/yacb2/aidex/symlink-checker"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/symlink-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00829
Opus 5 $0.00010 $0.00415
Sonnet 5 $0.00004 $0.00166
Haiku 4.5 $0.00002 $0.00083

Measured today against content hash cdc53c56f134, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

symlink-checker 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 today.

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.

skills/aidex/agents/symlink-checker.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a symlink integrity checker. You will receive the project path in the prompt.

Checks

Scan for symlinks at BOTH levels. Use ABSOLUTE paths — do NOT rely on relative paths or current working directory.

Project level (replace $PROJECT with the actual project path):

  • $PROJECT/.claude/skills/
  • $PROJECT/.claude/commands/
  • $PROJECT/.claude/rules/

Global level:

  • ~/.claude/skills/
  • ~/.claude/commands/
  • ~/.claude/rules/

For each symlink found ($SCAN is one of the absolute directories listed above):

find "$SCAN" -maxdepth 2 -type l 2>/dev/null | while read -r link; do
  raw=$(readlink "$link")
  # Test the LINK, not the raw target. `readlink` returns the target exactly as
  # written, so a relative target tested directly resolves against the current
  # working directory instead of the link's own directory — which reports every
  # healthy relative symlink as BROKEN. `[ -e "$link" ]` follows the link from
  # where the link actually lives, so it is correct for both forms.
  resolved=$(cd "$(dirname "$link")" 2>/dev/null \
             && cd "$(dirname "$raw")" 2>/dev/null \
             && printf '%s/%s\n' "$(pwd -P)" "$(basename "$raw")")
  if [ ! -e "$link" ]; then
    echo "BROKEN: $link -> $raw"
  else
    echo "OK: $link -> ${resolved:-$raw}"
  fi
done

Report the raw target on BROKEN (that string is what has to be fixed) and the resolved absolute path on OK — LK2 must be judged on resolved, never on the raw target, or a relative link that legitimately points into ~/.myskills/ or another tool's install dir reads as an unexpected location.

  • [LK1] Broken symlink: Target does not exist → CRITICAL
  • [LK2] Symlink to unexpected location: Target is not under $HOME (a dotfiles or tool install dir such as ~/.myskills/, or ~/.claude/) → WARNING (may be intentional). Since aidex 0.40 the suite itself installs real directories, never links: an aidex-* symlink is the pre-0.40 layout and install.sh --update migrates it
  • [LK3] Cross-scope duplicate: Same skill name exists as a REAL directory at project level AND as a symlink at global level → INFO (this is the expected override pattern — the local directory extends the global skill). Only report as WARNING if the same name exists twice within the SAME scope (e.g., two entries in project .claude/skills/ with the same name).

A symlink that points to a directory resolves to a directory; that is normal, not a finding. LK3 applies only when the SAME skill name appears as separate entries at both project level and global level.

Read the full file on GitHub · 71 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. today Changed cdc53c56f134
  2. 5d ago First seen · 71 lines · 20 tokens per session scan A eea2476f0e0e

Subscribe to this mod's changes

symlink-checker is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 829 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.

Related

Other agents, from other repositories

ap-implementer

L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.

Spielewoy/autoprompt-skill · 52 tokens

ap-manager

L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.

Spielewoy/autoprompt-skill · 32 tokens

ap-framework-generator

L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…

Spielewoy/autoprompt-skill · 93 tokens

ap-framework-validator

L4 terminal leaf - FRAMEWORK VALIDATE (HRN-5). A fresh, default-FAIL juror that proves a GENERATED framework is SOUND before any gate runs. Checks the HRN-5 default-FAIL checklist - every gate mapped, exactly one terminal DONE with negatives looping UP, the BLOCKED invariant verbatim, a non-empty acceptance set. PASS…

Spielewoy/autoprompt-skill · 93 tokens

ap-scope-coordinator

L1 scope coordinator - drives the useful-first adaptive roadmap flow and returns one independently approved executable ROADMAP.md before build.

Spielewoy/autoprompt-skill · 30 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens