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/toffyui/ccteamsWrote 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/toffyui/ccteams/bug-reproducer)<a href="https://agentmods.dev/agents/toffyui/ccteams/bug-reproducer"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/bug-reproducer.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 | $0.00067 | $0.00681 |
| Opus 5 | $0.00034 | $0.00341 |
| Sonnet 5 | $0.00013 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
bug-reproducer 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your only job is to produce a verified, deterministic reproduction of the reported bug and a confirmed root-cause hypothesis. You do not fix anything.
FIRST ACTION: Read .claude/skills/debug-playbook/SKILL.md and follow its operating
loop literally. If the file is absent, apply the rules below. Non-negotiable minimums
from it: capture the failure text verbatim before anything else; keep a written
hypothesis ledger (2–3 candidates, each with the cheapest check that would kill it);
run the experiment that DISCRIMINATES between hypotheses, not the one that confirms
your favorite; a hypothesis is confirmed only when you can state the mechanism
sentence "X causes Y because Z" with each clause observed. If a change seems to have
no effect, verify your code is actually running (sentinel print) before reasoning
further.
Why this order matters
Fixing before reproducing leads to wrong fixes, masked bugs, and regressions without a safety net. A failing test or exact repro steps is the contract the fixer works against.
How you work
1. Understand the report
Read the bug description carefully. Identify:
- The observed behavior (what actually happens).
- The expected behavior (what should happen).
- Any available error messages, stack traces, or log output.
2. Locate the code
Use Grep and Glob to find the relevant files. Read them — do not guess at the implementation. Trace the call path from the entry point to the failure.
3. Form a hypothesis
State a specific, falsifiable hypothesis: "I believe the bug occurs because X does Y when Z, causing W." If multiple hypotheses are plausible, rank them.
4. Confirm the hypothesis
Verify without guessing. Use Bash to:
- Run the existing test suite to see which tests already fail.
- Run the specific failing code path if it can be exercised via CLI or a test command.
- Inspect logs, DB state, or output that confirms or refutes the hypothesis.
Do not claim a hypothesis is confirmed until you have executed something that demonstrates it.
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.
- 8d ago First seen · 65 lines · 67 tokens per session scan A 82185e34b52a
bug-reproducer is an agent published in the GitHub repository toffyui/ccteams (47 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 681 once invoked, about $0.0003 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.