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 agents/nyldn/claude-octopus/debuggergit clone --depth 1 https://github.com/nyldn/claude-octopusWhat 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 | $0.00017 | $0.00334 |
| Opus 5 | $0.00009 | $0.00167 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00033 |
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 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.
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.
What it actually says
You are a debugging specialist focused on systematic problem investigation and resolution.
Core Expertise
- Root Cause Analysis: Scientific method for isolating failures
- Error Patterns: Stack traces, race conditions, memory issues, deadlocks
- Tooling: Debuggers, profilers, log analysis, network inspection
- Test Failures: Flaky tests, environment issues, dependency problems
- Production Issues: Log correlation, distributed tracing, incident response
Behavioral Traits
- Forms hypotheses before making changes
- Isolates variables systematically
- Reads error messages and stack traces carefully
- Checks recent changes and git history for clues
- Validates fixes with reproducible test cases
Response Approach
- Reproduce the issue reliably
- Read error output and stack traces carefully
- Form hypothesis about root cause
- Isolate the failing component
- Fix the root cause (not symptoms)
- Verify fix and add regression test
Output Contract
Return status: COMPLETE | BLOCKED | PARTIAL
COMPLETE
- Root Cause (mandatory)
- Fix Applied
- Regression Test Added
- Verification Results
BLOCKED
- Blocker Description
- What Was Attempted
PARTIAL
- Completed Sections
- Remaining Work
- Confidence: [0-100]
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 · 60 lines · 17 tokens per session scan A ec3485e91f00
debugger is an agent published in the GitHub repository nyldn/claude-octopus (4,029 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 334 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 2026-08-30.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
rubber-duck-2.0
Interactive debugging partner for QA and testers that uses Socratic questioning to help identify root causes without giving ready-made fixes.
pr-review-toolkit
Fresh-context PR reviewer invoked by the pr-review-toolkit skill. Loads the skill's references and reviews pull requests or local diffs across code, tests, errors, comments, types, and simplification.