Borrowing it
Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/fix-links/SKILL.mdgit clone --depth 1 https://github.com/banshee-data/velocity.reportWrote 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/banshee-data/velocity.report/fix-links)<a href="https://agentmods.dev/skills/banshee-data/velocity.report/fix-links"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/fix-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/banshee-data/velocity.report/fix-links"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/fix-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 | $0.00032 | $0.01203 |
| Opus 5.5 | $0.00013 | $0.00481 |
| Sonnet 5.5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade C, and why
fix-links scanned grade C with 1 finding 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.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
| Path root is wrong (e.g. `.github/TENETS.md` exists but ref uses bare name) | Update to the location that exists <!-- link-ignore --> | How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: fix-links
Audit all Markdown files for dead Markdown links and stale `backtick/paths`,
fix those that can be resolved automatically, and surface anything ambiguous
to the operator with a clear decision prompt.
Usage
/fix-links
/fix-links .claude/agents/
/fix-links docs/plans/some-plan.md
Procedure
1. Run both link checkers
python3 scripts/check-relative-links.py --report 2>&1
python3 scripts/check-backtick-paths.py --report 2>&1
Collect every finding into a working list. If both checkers report clean, print "All links OK: nothing to fix." and stop.
2. Triage each finding
For every item apply this decision tree in order:
a. Placeholder or template token: skip silently.
Examples: entries like linked-plan-name.md or other-plan.md
in docs/plans/TEMPLATE.md. These are intentional scaffolding.
b. The file moved: unique match exists; fix automatically. Search the repo for the bare filename:
find . -name "<filename>" \
! -path "*/node_modules/*" ! -path "*/.venv/*" \
! -path "*/.git/*" ! -path "*/.build/*" \
! -path "*/DerivedData/*"
If exactly one result is found, compute the correct relative or repo-root path and apply the edit. Record it in the Fixed list.
c. Multiple candidates exist: surface to operator (see §3).
d. No match anywhere in the repo: surface to operator (see §3).
e. The reference is to a file that should exist but has not been created yet (e.g. a plan references a future schema file): surface to operator as "referenced file not yet created".
3. Surface ambiguous cases
After exhausting automatic fixes, print a Needs operator decision section formatted as a numbered list. For each item include:
- The file and line number
- The broken reference as written
- What was searched for and what (if anything) was found
- A concrete question: "Should this link be removed, updated to X, or left as-is?"
Example format:
## Needs operator decision
1. docs/lidar/architecture/vector-scene-map.md:13
Reference: `../lidar/architecture/ground-plane-extraction.md`
Searched for: ground-plane-extraction.md
Found: (no match anywhere in repo)
Question: Has this document been deleted, renamed, or not yet written?
Options: (a) remove the reference, (b) update to the new path, (c) leave as a known gap
2. data/structures/MATRIX.md:17
Reference: `../../.github/agents/matrix-tracer.agent.md`
Searched for: matrix-tracer.agent.md
Found: (no match anywhere in repo)
Question: Was matrix-tracer.agent.md removed intentionally?
Options: (a) remove the reference, (b) create the file, (c) update to the replacement path
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 · 151 lines · 32 tokens per session scan C 1db828ac19c4
fix-links is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,203 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
fix-links compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fix-linksbanshee-data/velocity.report | Skill | 11 | today | Apache-2.0 | C | 32 | Claude Code |
| analyzing-network-traffic-for-incidentsmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 91 | Claude Code |
| analyzing-network-packets-with-scapymukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 75 | Claude Code |
| analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | B | 49 | Claude Code |
| whitebox-toolsznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 119 | Claude Code, Codex |
| performing-network-packet-capture-analysisxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | C | 62 | Claude Code, Codex |
| pdalznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | B | 90 | Claude Code, Codex |