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 skills add hcaiano/skills --skill debug-modegit clone --depth 1 https://github.com/hcaiano/skillsWrote 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/hcaiano/skills/debug-mode)<a href="https://agentmods.dev/skills/hcaiano/skills/debug-mode"><img src="https://agentmods.dev/badge/skills/hcaiano/skills/debug-mode/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/hcaiano/skills/debug-mode"><img src="https://agentmods.dev/badge/skills/hcaiano/skills/debug-mode.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 | $0.00041 | $0.00828 |
| Opus 5.5 | $0.00016 | $0.00331 |
| Sonnet 5.5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
debug-mode 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 20d 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.
its exact symptom: a failing test, a curl script, a CLI run on a fixture, a How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Mode
Fix only a proven cause; a plausible fix that passes once proves nothing. Already inside a debug-mode run → continue the loop.
Respect the user's verb: diagnose ends before Fix and applies no fix;
remove every temporary log before its report.
debug, or a bug report with no verb, runs through Fix.
Workflow
- Understand. Done when symptoms, affected surface, expected behavior, actual behavior, and a reproduction path are known.
- Red loop. Build one command that drives the bug's code path and asserts its exact symptom: a failing test, a curl script, a CLI run on a fixture, a headless-browser script, a replayed trace. Make it tight: deterministic, fast, runnable unattended, asserting the symptom rather than "didn't crash". For a flaky bug, raise the reproduction rate (loop the trigger, add stress) until it is debuggable. For slow code, the loop is a baseline measurement (timing harness, profiler, query plan, production traces) that goes red above a stated threshold. When no command is practical (auth-walled, user-specific, production-only), say so and rely on instrumentation in steps 5-6. Done when the command has run red on this bug, or its absence is stated.
- Minimize. With a loop, shrink the repro one cut at a time (inputs, callers, config, data, steps), rerunning the loop after each cut. Done when every remaining part matters: removing any one turns the loop green. Without a loop, go straight to step 4.
- Hypothesize. Done when 2-3 ranked hypotheses each name the observation that would confirm or reject it.
- Instrument. For slow code, profile the minimized repro or bisect
between known-good and known-bad states (
git bisect runwith the loop). Otherwise add temporary logs. Done when the observations distinguish the hypotheses without leaking secrets or changing the behavior; if they change it, observe from a less invasive point. - Reproduce. Done when the bug has been triggered and the evidence collected, through the loop when one exists. If the flow is auth-walled or user-specific, ask the user to reproduce and wait.
- Analyze. Done when evidence confirms one hypothesis or rejects every current one explicitly. When it rejects them all, write new hypotheses from the evidence and return to step 5.
- Fix. When a seam exercises the real bug pattern, turn the minimized repro into a regression test first. Done when the smallest evidence-backed fix is applied, the loop (when one exists) has gone green on the original scenario, and every temporary log is removed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed · -36 lines · -1 tokens per session a3292e8b2277
- 1mo ago First seen · 112 lines · 42 tokens per session scan A 15020d5d47bb
debug-mode is a skill published in the GitHub repository hcaiano/skills (3 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 828 once invoked, about $0.0002 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 skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).