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 skills add richfrem/agent-plugins-skills --skill symlink-managergit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/skills/richfrem/agent-plugins-skills/symlink-manager)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/symlink-manager"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/symlink-manager/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.
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/symlink-manager"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/symlink-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
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 →
- high Anti-Refusal · line 41 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Anti-Refusal · line 113 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 41 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high Prompt Injection · line 113 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high Anti-Refusal · line 62 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Tool Misuse · line 66 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 112 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00180 | $0.01730 |
| Opus 5 | $0.00090 | $0.00865 |
| Sonnet 5 | $0.00036 | $0.00346 |
| Haiku 4.5 | $0.00018 | $0.00173 |
Grade A, and why
symlink-manager 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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Symlink Manager — Cross-Platform Skill
The Core Problem
Git symlinks break across platforms because:
| Issue | macOS/Linux | Windows |
|---|---|---|
| Git setting | core.symlinks=true (default) |
core.symlinks=false (default, unless Dev Mode enabled) |
| Link type | ln -s symlink |
NTFS symlink or Junction Point or Hardlink |
| Permissions | Any user | Requires Developer Mode or admin elevation |
| Git behaviour | Stores as symlink object | Stores as plain text file containing the target path |
When core.symlinks=false, Git checks out a symlink as a plain text file whose contents are the target path. When you then git pull on the other machine, that text file arrives instead of a real link — silent, no error.
The Hardlink Trap
When core.symlinks=false and Developer Mode is disabled, symlinks can be accidentally replaced with hardlinks. Hardlinks cannot be committed as symlinks to Git, so they break the cross-platform workflow:
- macOS user commits real symlinks (core.symlinks=true by default)
- Windows user with Developer Mode off: symlinks checkout as plain-text files, then get replaced with hardlinks
- Windows user pushes: Git sees plain-text file, commits it as a file, not a symlink
- macOS user pulls: receives text file instead of symlink — broken
Solution: Always use real symlinks, never hardlinks. Enable Developer Mode on Windows first, then use /create-sym-link command to create proper symlinks that Git recognizes.
Workflow
Step 1 — Diagnose the environment
Run the diagnosis script first. It checks:
- OS and Python version
git config core.symlinks(local + global)- Whether Developer Mode is active (Windows)
- Whether the script is running as admin (Windows)
- Existing symlinks vs broken links vs text-file stand-ins in the repo
python ./scripts/symlink_manager.py diagnose
Step 2 — Fix Git config
On Windows (needs Developer Mode enabled first, or run as admin):
git config core.symlinks true
git rm --cached -r . # unstage everything
git reset --hard # re-checkout with symlinks honoured
What ships with it
6 files 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.
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.
- 2d ago Changed · -1 lines f15e644939d5
- 5d ago First seen · 174 lines · 180 tokens per session scan A c3568196792f
symlink-manager is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 180 tokens to every session and 1,730 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
review-pr
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
create-pr
Create a pull request (GitHub) or merge request (GitLab) from the current branch.
respond-github
Respond to a GitHub issue/PR or GitLab issue/MR.
pr-deslop
Use when cleaning AI slop, verbose commit messages, brittle references, or low-value changes from a branch before review.
changelog
Generate CHANGES entries from branch commits and PR context.