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 agentmods add skills/metaspartan/cybara/api-debugnpx skills add metaspartan/cybara --skill api-debuggit clone --depth 1 https://github.com/metaspartan/cybaraWhat 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 | $0.00028 | $0.00651 |
| Opus 5 | $0.00014 | $0.00326 |
| Sonnet 5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
api-debug scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"cybara":{"requires":{"anyBins":["curl","python3"]}}} How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Debug
Use this when an API returns the wrong status/body, auth fails, a webhook does not arrive, pagination is suspicious, GraphQL returns errors, or code works in one client but not another.
Principle
Isolate the failing layer before changing code:
- Connectivity
- TLS and proxy behavior
- Authentication
- Request shape
- Response parsing
- Semantic correctness
- Retry, timeout, and rate-limit behavior
REST Checks
Use curl for the smallest repro. Keep tokens in environment variables and never paste full secrets into chat or logs.
curl -v --connect-timeout 5 https://api.example.com/health
curl -sS -D /tmp/headers.txt -o /tmp/body.json https://api.example.com/resource
python3 -m json.tool /tmp/body.json
For JSON POSTs:
curl -sS -v -X POST "$URL" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOKEN" \
--data '{"key":"value"}'
GraphQL Checks
GraphQL failures often return HTTP 200. Always inspect errors.
curl -sS -X POST "$GRAPHQL_URL" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOKEN" \
--data '{"query":"{ viewer { id } }"}' | python3 -m json.tool
If errors exists, debug query shape and permissions even when the HTTP status is 200.
Auth Checks
- Confirm scheme:
Bearer,Basic,Token,X-Api-Key, signed request, OAuth cookie. - Confirm environment: staging token against staging host.
- Confirm expiry for JWTs without printing the full token:
python3 - <<'PY'
import base64, json, os, time
tok = os.environ["TOKEN"]
payload = tok.split(".")[1]
payload += "=" * (-len(payload) % 4)
data = json.loads(base64.urlsafe_b64decode(payload))
print({k: data.get(k) for k in ("iss", "aud", "sub", "exp")})
print("expired:", data.get("exp", 0) < time.time())
PY
Webhooks
- Capture raw request body and headers before parsing.
- Verify signature over the exact raw bytes, not a reserialized JSON object.
- Check timestamp skew and replay windows.
- Store a failing fixture and make a regression test for signature parsing.
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 · 88 lines · 28 tokens per session scan A 9303ace45320
api-debug is a skill published in the GitHub repository metaspartan/cybara (23 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 651 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
gws-calendar
Google Calendar: Manage calendars and events.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.