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 checking-linksgit 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/checking-links)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/checking-links"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/checking-links/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/checking-links"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/checking-links.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00586 |
| Opus 5.5 | $0.00009 | $0.00234 |
| Sonnet 5.5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
checking-links 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checking Links (checking-links)
Audits and repairs broken documentation and image references across repositories using a strict 5-step pipeline.
Contents
Critical Constraints
- Pipeline Order: Run steps strictly in sequence: 1 -> 2 -> 3 -> 4 -> 5. Never skip inventory or audit.
- Clean Git State: Verify git working tree is clean before running Step 4 (
--dry-runfirst). - Scope Restriction: Step 4 only auto-corrects unambiguous markdown/image links; code paths in
.py/.jsare never modified. - No Guessing: Ambiguous link targets matching multiple files are left for manual user review in Step 5.
Quick start
Execute the complete 5-step audit and autofix pipeline:
python3 scripts/01_build_file_inventory.py && \
python3 scripts/02_extract_link_references.py && \
python3 scripts/03_audit_broken_links.py && \
python3 scripts/04_autofix_unique_links.py --dry-run
Workflow
- Step 1 (Inventory): Run
scripts/01_build_file_inventory.pyto index all valid filenames in repository. - Step 2 (Extraction): Run
scripts/02_extract_link_references.pyto extract all link/path strings with line numbers. - Step 3 (Audit): Run
scripts/03_audit_broken_links.pyto audit references against the file inventory. - Step 4 (Auto-Fix): Run
scripts/04_autofix_unique_links.py --dry-runto preview fixes, followed by--backupto apply. - Step 5 (Report): Run
scripts/05_report_unfixable_links.pyto produceunfixable_links_report.md.
Verification
Confirm zero remaining broken links or review unfixable report:
test -f broken_links.json && python3 -c "import json; d=json.load(open('broken_links.json')); print(f'Broken links: {len(d)}')"
References
- acceptance-criteria.md — QA verification criteria for the link checker pipeline.
- fallback-tree.md — Failure triage and recovery tree for missing artifacts or broken scripts.
What ships with it
13 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.
- assets/diagrams/link_checker_workflow.png 50 B
- assets/diagrams/link-checker-workflow.mmd 1.0 KB
- assets/diagrams/logic.mmd 851 B
- assets/diagrams/workflow.mmd 996 B
- evals/evals.json 707 B
- evals/results.tsv 301 B
- references/acceptance-criteria.md 2.2 KB
- references/fallback-tree.md 2.0 KB
- scripts/01_build_file_inventory.py 2.5 KB runs code
- scripts/02_extract_link_references.py 4.6 KB runs code
- scripts/03_audit_broken_links.py 4.0 KB runs code
- scripts/04_autofix_unique_links.py 9.5 KB runs code
- scripts/05_report_unfixable_links.py 3.4 KB runs code
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.
- yesterday First seen · 58 lines · 23 tokens per session scan A 7551270dea85
checking-links is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 586 once invoked, about $0.0001 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 2026-10-24.
Other skills, from other repositories
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…