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 commands/hi0001234d/coding-agent-mcp-tools/debuggit clone --depth 1 https://github.com/hi0001234d/coding-agent-mcp-toolsWhat 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 | $0.00027 | $0.00432 |
| Opus 5 | $0.00014 | $0.00216 |
| Sonnet 5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
autoresearch: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 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
EXECUTE IMMEDIATELY — do not deliberate, do not ask clarifying questions before reading the protocol.
Argument Parsing (do this FIRST)
Extract these from $ARGUMENTS — the user may provide extensive context alongside flags. Ignore prose and extract ONLY flags/config:
--fix— if present, auto-switch to /autoresearch:fix after finding bugs--scope <glob>orScope:— file globs to investigate--symptom "<text>"orSymptom:— description of what's broken--severity <level>— minimum severity to report (critical/high/medium/low)--technique <name>— force a specific investigation technique (binary-search, differential, minimal-reproduction, trace, pattern-search, working-backwards, rubber-duck)Iterations:or--iterations N— integer for bounded mode (CRITICAL: run exactly N iterations then stop)
If Iterations: N or --iterations N is found, set max_iterations = N. Track current_iteration starting at 0. After iteration N, print final summary and STOP.
All remaining text in $ARGUMENTS is additional context — use it to understand the problem but do not treat it as flags.
Execution
- Read the debug workflow:
.claude/skills/autoresearch/references/debug-workflow.md - If scope or symptom is missing — use
AskUserQuestionwith batched questions per debug-workflow.md - Execute the 7-phase debug loop
- If bounded: after each iteration, check
current_iteration < max_iterations. If not, STOP and print summary.
Stream all output live — never run in background.
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 · 32 lines · 27 tokens per session scan A 97524b89389c
autoresearch:debug is a command published in the GitHub repository hi0001234d/coding-agent-mcp-tools (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 432 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 commands, from other repositories
notebook-review
Comprehensive review of Jupyter notebooks and Python scripts.
cross-validate
Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.
translate-id
Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…
autoprove
Autonomous multi-cycle theorem proving with explicit stop budgets.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
paperfit-undo
作用: 恢复最近一次 PaperFit 自动写回前的备份版本，优先回滚主 .tex，必要时一并恢复 data/state.json。.