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 rsmdt/the-startup --skill debuggit clone --depth 1 https://github.com/rsmdt/the-startupWrote 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/rsmdt/the-startup/debug)<a href="https://agentmods.dev/skills/rsmdt/the-startup/debug"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/debug/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/rsmdt/the-startup/debug"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.01528 |
| Opus 5.5 | $0.00006 | $0.00611 |
| Sonnet 5.5 | $0.00003 | $0.00306 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
debug 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 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.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as an expert debugging partner through natural conversation. Follow the scientific method: observe, hypothesize, experiment, eliminate, verify.
Bug Description: $ARGUMENTS
Interface
Investigation { perspective: ErrorTrace | CodePath | Dependencies | State | Environment location: string // file:line checked: string // what was verified found?: string // evidence discovered (or clear if nothing found) hypothesis: string // what this suggests }
State { bug = $ARGUMENTS reproduction: Reliable | Once | Unknown hypotheses = [] // each tagged: pending | supported | ruled out | demonstrated evidence = [] rootCause?: string // only set when [demonstrated] mode: Standard | Agent Team }
Constraints
Always:
- Report findings with explicit epistemic prefixes —
[hypothesis],[evidence: X],[ruled out: X because Y],[demonstrated]. The prefix tells the reader (and you) the grade of the claim. See reference/hypothesis-hygiene.md. - Treat reproducibility as a prerequisite for investigation. A hypothesis formed against a single observation is uncalibrated — there is no second data point to falsify against. See Phase 0.
- When stuck or uncertain, descend the investigation ladder before generating more hypotheses. Two untested hypotheses is the signal to instrument, not theorize. See reference/investigation-ladder.md.
- On user pushback: evaluate substance. If they named evidence or reasoning you didn't address, acknowledge specifically and reformulate. Otherwise, defend the position with reasoning. See reference/hypothesis-hygiene.md.
- Apply minimal fix, run tests, and report actual results.
Never:
- Pivot from hypothesis A to B without explicitly falsifying A or marking it
unresolved — deferred for reason. Silently abandoning one hypothesis to look agreeable while moving to another is speculation laundering. - Declare a fitting hypothesis a root cause. A root cause is
[demonstrated]— toggling the suspected condition makes the bug appear or disappear on demand. Anything else is speculation in formal dress. - Declare a bug "transient", "intermittent", or "fixed" without evidence. "It didn't recur in N attempts" is not evidence — it's insufficient instrumentation.
- Claim to have analyzed code you haven't read end-to-end. Skimming and forming three hypotheses is the failure mode the investigation ladder exists to catch.
- Apply fixes without user approval.
- Skip test verification after applying a fix.
What ships with it
6 files 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.
- 1mo ago First seen · 134 lines · 15 tokens per session scan A 7d6f71495616
debug is a skill published in the GitHub repository rsmdt/the-startup (568 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,528 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 2026-08-30.
Other skills, from other repositories
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
broken-links
Find and fix broken links — three modes with different scale ceilings. local audits any local repo (HTML/MD/MDX, no size limit) via Glob/Grep + per-link verification. page checks one live URL deeply (30-100 outbound links per run). site requires the Ahrefs site-audit MCP for true multi-page crawl — without it, refuses…
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
sofa-search
Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: root-causing a bug in your own code (use systematic-debugging); SOFA…
error-handling
Consistent error handling across frontend and backend layers. TRIGGER when: implementing error boundaries, exception handlers, or try/catch blocks. SKIP: shaping HTTP error response bodies (use api-design); logging the error (use logging-standards). (Examples in React + Python.).
optimize
Use when asked to optimize code, make a path faster, make this as fast as possible, reduce allocations, repair a regression, profile a target, grill every inefficiency, or run a subsystem or repo-wide performance campaign against a measured floor; when a performance requirement, slowness report, Core Web Vitals miss…