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/0xsoftboi/suwappubot/bugclassgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/commands/0xsoftboi/suwappubot/bugclass)<a href="https://agentmods.dev/commands/0xsoftboi/suwappubot/bugclass"><img src="https://agentmods.dev/badge/commands/0xsoftboi/suwappubot/bugclass.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 | $0.00039 | $0.00455 |
| Opus 5 | $0.00019 | $0.00228 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
bugclass 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 4d 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
Bug-Class Elimination
Formalizes the pattern that produced the best sessions here: root-cause one crash, then sweep for its siblings (one chart crash → seven patched null-guard sites).
Input: $ARGUMENTS — one confirmed bug. If empty, ask for it; do not guess.
Step 1 — Reproduce first
Write a failing test that reproduces the bug before touching any source. If you can't make it fail, you haven't understood it — stop and say so.
Step 2 — Fix minimally
Fix, confirm the test passes. One focused commit.
Step 3 — Name the class
Articulate the bug class in one sentence (e.g. "chart render paths assume unique timestamps", "null-unguarded access on optional API fields"). This sentence is the search spec.
Step 4 — Sweep
Dispatch scout (haiku) to grep/AST-search both stacks for every other instance. Write results to .progress/bug-class-queue.md with file:line + risk rating. This file is the durable state — an interrupted session resumes from it.
Step 5 — Work the queue, one item at a time
For each entry: reproducing test → fix → full suite → one focused commit per instance with a message naming the instance.
- Update
.progress/bug-class-queue.mdafter every single item (done / skipped / needs-human). - Bash
timeoutof at least600000ms on test runs. A slow suite is not a hang. - If a fix needs a design decision or would balloon into a refactor: skip it, log under
NEEDS HUMAN, move on. Do not expand scope.
Step 6 — Report
Instances found / fixed / skipped-with-reason, total test-count delta, and whether any instance touches a money path (→ money-path-reviewer before merge).
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.
- 4d ago First seen · 31 lines · 39 tokens per session scan A c08aed388cf2
bugclass is a command published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 455 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 2026-08-30.
Other commands, from other repositories
debug-order
Debug why a CoW Protocol order failed to match.
krait
Run a complete multi-phase security audit on the target codebase.
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
krait-init
Standalone readiness check before running /krait. Verifies tools, project shape, gitignore, MCP wiring, and /.claude install. Reports what's missing — does NOT install or modify anything.
dashboard
Open the ChainGPT marketplace dashboard (localhost web UI — Overview, Skills, Activity, Health, About).