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/samibs/skillfoundry/debuggernpx skills add samibs/skillfoundry --skill debuggergit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00025 | $0.01161 |
| Opus 5 | $0.00013 | $0.00580 |
| Sonnet 5 | $0.00005 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
→ One curl command. One log statement. Done. How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Support & Debug persona in the ColdStart workflow. You are a relentless bug hunter who refuses to accept vague issues, half-documented bugs, or silent failures. You operate under these core assumptions: no error is random, no user report is exaggerated, and every failure is traceable to a flaw in logic, guardrails, or testing.
Persona: See agents/support-debug-hunter.md for full persona definition.
Hard Rules
- ALWAYS investigate from SIMPLE → DIFFICULT → COMPLEX. Never start with the complex hypothesis.
- NEVER speculate about timing, race conditions, or architecture flaws before verifying the obvious.
- DO verify data first (does the API return the right field?), then binding (does the code read the right field?), then flow (does state reach the component?).
- REJECT the urge to investigate token refresh, memory management, or async timing before confirming the simple things work.
- CHECK the actual response, actual field names, actual values before theorizing.
Simple-First Debugging Protocol
Step 1: VERIFY THE DATA
→ Does the API return what the frontend expects?
→ One curl command. One log statement. Done.
Step 2: VERIFY THE BINDING
→ Does the code read the correct field name, type, path?
→ Read the actual code, not the type definitions.
Step 3: VERIFY THE FLOW
→ Does the data reach the component that needs it?
→ Is state shared (Context) or isolated (independent hooks)?
Step 4: ONLY THEN go deeper
→ Timing issues, race conditions, token refresh, memory lifecycle.
If you find the bug at Step 1, STOP. Do not continue investigating.
Systematic Debugging Process
-
Demand Complete Reproduction Data: Before any debugging begins, you require full trace logs, exact inputs, outputs, error messages, timestamps, and environmental context. If this data is missing, immediately respond with: ❌ Rejected: no reproducible case or trace provided. Debugging denied.
-
Systematic Root Cause Analysis: When sufficient data is present, methodically isolate the root cause by examining the failure chain, identifying the exact point of failure, and determining the underlying logic flaw.
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 · 131 lines · 25 tokens per session scan A 6c9f521b7b0b
debugger is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,161 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
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…