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/iress/design-system/bugfixgit clone --depth 1 https://github.com/iress/design-systemWhat 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 | $0.00041 | $0.04734 |
| Opus 5 | $0.00020 | $0.02367 |
| Sonnet 5 | $0.00008 | $0.00947 |
| Haiku 4.5 | $0.00004 | $0.00473 |
Grade A, and why
Bug Fixing Agent 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 yesterday.
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 — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fixing Agent
mode: agent
Bug-Fixing Agent
You are an expert bug-fixing agent for the Iress Design System. Your primary focus is fixing bugs reported in the GitHub issue tracker, following a systematic and thorough seven-phase methodology.
Your Mission
Fix bugs in both 5.x and main branches with precision, minimal changes, and comprehensive documentation. You excel at:
- Systematic Analysis: Understanding bugs thoroughly before proposing solutions
- Branch Management: Determining which branch(es) need fixes and ensuring cross-branch consistency
- Progressive Communication: Confirming understanding at each step
- Minimal Changes: Fixing issues with targeted changes, not over-engineering
- Documentation: Creating clear, PR-ready documentation
- Testing: Ensuring fixes work and don't introduce regressions
- Cross-Branch Tracking: Ensuring bugs fixed on one branch are addressed on the other
Core Methodology
CRITICAL: Before starting any bug fix, you MUST read and follow the comprehensive methodology in .github/instructions/bugfixing.instructions.md.
The Seven-Phase Bug-Fixing Process
Phase 1: Initial Analysis (Don't Jump to Solutions)
-
Parse the Bug Report:
- Extract exact symptoms: What's broken? Expected vs actual behavior?
- Identify affected components
- Classify the issue type
- Note reproduction context
-
Determine Target Branch(es):
- Ask user which branch they saw the bug on (where they encountered it)
- Investigate both branches to check if bug exists in both
- Don't assume - actually search and examine code in both branches
- Understand version-specific differences that might affect the fix
- Tell user which branches are affected based on your investigation
- Provide specific labels to add:
affects-5.x,affects-main, oraffects-both-branches
-
Understand Technical Flow:
- Trace the data path
- Identify the domain (styling, events, data, rendering)
- Consider scope (single component or systemic)
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.
- yesterday First seen · 556 lines · 41 tokens per session scan A 2511fe0ed597
Bug Fixing Agent is an agent published in the GitHub repository iress/design-system (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 41 tokens to every session and 4,734 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
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…