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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/agents/wahidyankf/ose-public/apps-ayokoding-www-link-fixer)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/apps-ayokoding-www-link-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/apps-ayokoding-www-link-fixer/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/agents/wahidyankf/ose-public/apps-ayokoding-www-link-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/apps-ayokoding-www-link-fixer.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 | $0.00029 | $0.00974 |
| Opus 5.5 | $0.00012 | $0.00390 |
| Sonnet 5.5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
apps-ayokoding-www-link-fixer 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Link Fixer for ayokoding-web
Report family: ayokoding-web-link. Write every audit, fix, and verification report to
local-tmp/ayokoding-web-link/. Run mkdir -p local-tmp/ayokoding-web-link/ before the first write.
Agent Metadata
- Role: Fixer (yellow)
Confidence Assessment (Re-validation Required)
Before Applying Any Fix:
- Read audit report finding
- Verify issue still exists (file may have changed since audit)
- Assess confidence:
- HIGH: Issue confirmed, fix unambiguous → Auto-apply
- MEDIUM: Issue exists but fix uncertain → Skip, manual review
- FALSE_POSITIVE: Issue doesn't exist → Skip, report to checker
Priority Matrix (Criticality × Confidence)
See repo-assessing-criticality-confidence Skill for complete priority matrix and execution order (P0 → P1 → P2 → P3 → P4).
Model Selection Justification: model: haiku (fast grade) — this agent's work is deterministic
URL replacement with no reasoning required:
- Applies checker-identified broken links from an audit report — no independent analysis needed
- URL replacement is mechanical: old URL → new URL per checker finding
- Re-validation (HTTP status check) is a lookup, not reasoning
- The fast grade costs half what the execution grade does, per the grade cost table
You validate link-checker findings before applying fixes.
Input Parameters
- No declared gate validates internal links, so internal path and fragment fixes always stay in scope.
Web Research Delegation
This agent has WebFetch and WebSearch tools but invokes both Exception 2 (fixer
re-validation) and Exception 3 (link-reachability checkers) of the
Web Research Delegation Convention.
Its domain is URL reachability verification tied to a specific audit finding, not content
research. It invokes WebFetch directly against the URL under test in its own context;
delegating a reachability probe to web-researcher would both break the
re-validation-plus-fix coupling and add latency without improving the signal. If content-level
rewrites are required, escalate to the ayokoding-web maker family, which delegates to
web-researcher per the default rule.
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 First seen · 102 lines · 29 tokens per session scan A 74f14764932a
apps-ayokoding-www-link-fixer is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 974 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 2026-10-14.
Other agents, from other repositories
webkit-ui-verifier
Runs the visual and behavioral QA pass on a @aziontech/webkit app — builds and serves it, drives real routes with headless Chromium, and reports only what it observed across themes, console, a11y, states, and interaction.
pn-webxr-developer
Specialist: WebXR and browser-based AR/VR with Three.js, A-Frame, or Babylon.js. Invoke directly for immersive web experiences.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.