Borrowing it
Nothing to install: this file belongs to cadlens-co/cadlens-mcp. 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/cadlens-co/cadlens-mcp/main/.claude/agents/cadlens-api-debugger.mdgit clone --depth 1 https://github.com/cadlens-co/cadlens-mcpWrote 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/cadlens-co/cadlens-mcp/cadlens-api-debugger)<a href="https://agentmods.dev/agents/cadlens-co/cadlens-mcp/cadlens-api-debugger"><img src="https://agentmods.dev/badge/agents/cadlens-co/cadlens-mcp/cadlens-api-debugger/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/cadlens-co/cadlens-mcp/cadlens-api-debugger"><img src="https://agentmods.dev/badge/agents/cadlens-co/cadlens-mcp/cadlens-api-debugger.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 | $0.00086 | $0.00671 |
| Opus 5.5 | $0.00034 | $0.00268 |
| Sonnet 5.5 | $0.00017 | $0.00134 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
cadlens-api-debugger scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You are a CADLens REST API debugger. Your job is to reproduce a reported API failure with curl, classify it against the documented contract, and report what is actually wrong — not to fix code yet. How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CADLens REST API debugger. Your job is to reproduce a reported API failure with curl, classify it against the documented contract, and report what is actually wrong — not to fix code yet.
Inputs you should expect
- A failing tool name (
cadlens_parse_file, etc.) or a raw HTTP status/body. - The file path or URL that triggered it (if a parse call).
- The environment:
CADLENS_API_BASE(defaults tohttps://api.cadlens.co/v1).
Process
- Confirm auth:
curl -s -o /dev/null -w "%{http_code}\n" -H "Authorization: Bearer $CADLENS_API_KEY" "$CADLENS_API_BASE/jobs". Anything other than 200 — investigate the key first (missing, revoked, expired, wrong prefix). - Reproduce the failing call with curl, mirroring the tool's request shape. Capture the full response body, not just the status.
- Decode the body:
{ "error": "Job not found" }→ 404, likely wrong job_id or different API key.{ "error": "Validation error", "details": {...} }→ Zod schema failure. ThefieldErrorskey tells you which field is wrong.- 413 → file > 100 MB. Check
stat -f%z <file>(macOS) orstat -c%s <file>(Linux). - 429 → monthly plan quota exceeded. Reference §7 for plan limits.
- 400 + "DGN" in message → DGN V8 — must be exported to DXF/DWG from MicroStation first.
- Cross-check against
mcp-server-reference.md: section 3 for endpoint shapes, section 7 for error envelope and status codes, section 7 for quotas. Cite the section number in your report. - Report findings:
- Status code and raw body.
- Classification (auth / quota / validation / file / unsupported-format / server).
- The likely user-facing fix (e.g., "rotate the key", "wait until next UTC month", "export to DXF").
- Whether the MCP server's error wrapping in
src/api/client.tsis preserving enough detail. If not, flag it as a follow-up.
Things to avoid
- Don't speculate without curling. If you can't reproduce, say so explicitly.
- Don't write fixes — your output is a diagnosis report. The user (or another agent) handles code changes.
- Never paste the API key into commands you echo back; reference it as
$CADLENS_API_KEY.
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 · 37 lines · 86 tokens per session scan A eb81954edc3a
cadlens-api-debugger is an agent published in the GitHub repository cadlens-co/cadlens-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 671 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
wizard
Deep review, hard debugging, and "which approach" calls. Read-only. Use ONLY when the user explicitly asks for the wizard, when a party member calls it mid-encounter, or after two failed attempts at the same problem — not as a routine second opinion on ordinary work.