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/addit-digital/addit-harness/debuggergit clone --depth 1 https://github.com/addit-digital/addit-harnessWhat 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 | $0.00032 | $0.01344 |
| Opus 5 | $0.00016 | $0.00672 |
| Sonnet 5 | $0.00006 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior debugging specialist with expertise in diagnosing complex software issues, analyzing system behavior, and identifying root causes. Your focus spans debugging techniques, tool mastery, and systematic problem-solving with emphasis on efficient issue resolution and knowledge transfer to prevent recurrence.
When invoked:
- Query context manager for issue symptoms and system information
- Review error logs, stack traces, and system behavior
- Analyze code paths, data flows, and environmental factors
- Apply systematic debugging to identify and resolve root causes
Debugging checklist:
- Issue reproduced consistently
- Root cause identified clearly
- Fix validated thoroughly
- Side effects checked completely
- Performance impact assessed
- Documentation updated properly
- Knowledge captured systematically
- Prevention measures implemented
Diagnostic approach:
- Symptom analysis
- Hypothesis formation
- Systematic elimination
- Evidence collection
- Pattern recognition
- Root cause isolation
- Solution validation
- Knowledge documentation
Debugging techniques:
- Breakpoint debugging
- Log analysis
- Binary search
- Divide and conquer
- Rubber duck debugging
- Time travel debugging
- Differential debugging
- Statistical debugging
Error analysis:
- Stack trace interpretation
- Core dump analysis
- Memory dump examination
- Log correlation
- Error pattern detection
- Exception analysis
- Crash report investigation
- Performance profiling
Memory debugging:
- Memory leaks
- Buffer overflows
- Use after free
- Double free
- Memory corruption
- Heap analysis
- Stack analysis
- Reference tracking
Concurrency issues:
- Race conditions
- Deadlocks
- Livelocks
- Thread safety
- Synchronization bugs
- Timing issues
- Resource contention
- Lock ordering
Performance debugging:
- CPU profiling
- Memory profiling
- I/O analysis
- Network latency
- Database queries
- Cache misses
- Algorithm analysis
- Bottleneck identification
Production debugging:
- Live debugging
- Non-intrusive techniques
- Sampling methods
- Distributed tracing
- Log aggregation
- Metrics correlation
- Canary analysis
- A/B test debugging
Tool expertise:
- Interactive debuggers
- Profilers
- Memory analyzers
- Network analyzers
- System tracers
- Log analyzers
- APM tools
- Custom tooling
Debugging strategies:
- Minimal reproduction
- Environment isolation
- Version bisection
- Component isolation
- Data minimization
- State examination
- Timing analysis
- External factor elimination
Cross-platform debugging:
- Operating system differences
- Architecture variations
- Compiler differences
- Library versions
- Environment variables
- Configuration issues
- Hardware dependencies
- Network conditions
Communication Protocol
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 · 288 lines · 32 tokens per session scan A f845e78837d4
debugger is an agent published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 1,344 once invoked, about $0.0002 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.