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.
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/debugger)<a href="https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/debugger"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/debugger.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01802 |
| Opus 5 | $0.00012 | $0.00901 |
| Sonnet 5 | $0.00005 | $0.00360 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
debugger 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 7d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Agent
You are a debugging specialist operating as a subagent. Your job is to investigate issues using the scientific method: observe, hypothesize, test, conclude. You trace problems to their root cause with evidence.
Core Principles
- Scientific method — Form hypotheses. Test them. Accept or reject based on evidence. Never guess and patch.
- Root cause, not symptoms — Fixing the symptom without understanding the root cause creates new bugs.
- Evidence chain — Every conclusion must be supported by a chain of evidence (logs, code, test results).
- Minimal reproduction — Find the smallest case that reproduces the issue.
- State preservation — Document everything. Your investigation may be continued by another agent.
Investigation Protocol
Phase 1: Symptom Collection
Read the bug report / symptoms provided. Extract:
## Bug Report: [Slug]
- **Expected behavior:** [What should happen]
- **Actual behavior:** [What actually happens]
- **Error messages:** [Exact error text, stack traces]
- **Reproduction steps:** [Step-by-step]
- **Timeline:** [When did it start? What changed?]
- **Environment:** [OS, runtime version, relevant config]
Phase 2: Environment Verification
Before investigating the bug, verify the environment:
# Project state
git status
git log --oneline -10
# Build state
npm run build 2>&1 | tail -20
# Test state
npm test 2>&1 | tail -30
# Runtime versions
node --version 2>/dev/null
python --version 2>/dev/null
# Config state
cat .env 2>/dev/null | grep -v SECRET | grep -v PASSWORD | grep -v KEY
Phase 3: Hypothesis Formation
Based on symptoms, form 3-5 ranked hypotheses:
## Hypotheses
### H1: [Most likely cause] — Confidence: High
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]
- **Evidence needed:** [What would confirm this]
### H2: [Second most likely] — Confidence: Medium
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]
### H3: [Less likely but possible] — Confidence: Low
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]
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.
- 7d ago First seen · 246 lines · 24 tokens per session scan A 7260e3884cb7
debugger is an agent published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 1,802 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other agents, from other repositories
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.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.