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/vedanta/the-systemWrote 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/vedanta/the-system/bug-fixer)<a href="https://agentmods.dev/agents/vedanta/the-system/bug-fixer"><img src="https://agentmods.dev/badge/agents/vedanta/the-system/bug-fixer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/vedanta/the-system/bug-fixer"><img src="https://agentmods.dev/badge/agents/vedanta/the-system/bug-fixer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.02452 |
| Opus 5.5 | $0.00016 | $0.00981 |
| Sonnet 5.5 | $0.00008 | $0.00490 |
| Haiku 4.5 | $0.00004 | $0.00245 |
Grade C, and why
bug-fixer scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules package-lock.json The source is not reproduced here
Licensed LGPL-3.0
The repository is licensed LGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 428 lines · 39 tokens per session scan C f8d337a5d506
bug-fixer is an agent published in the GitHub repository vedanta/the-system (9 stars, last pushed 7mo ago), licensed LGPL-3.0. It adds 39 tokens to every session and 2,452 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.
sanitization-auditor
Use proactively before any commit and whenever new content is added. Scans tracked files for private-project leaks - upstream private project names, internal absolute paths, proprietary domain logic (financial / portfolio / trading / prediction / tax / advisory specifics), customer data, secrets, internal endpoints…
refuter-reproduction
Reproduction-first lens for bug-fix DoDs only — the original bug must be reproduced against pre-fix code before any fix claim is trusted. Read-only. Invoked only by mnm-verify, only when the DoD's Goal is a bug fix.
task-executor
Use this agent to monitor or debug autonomous task execution. Examples - "Why did my task fail?", "Show me the output from the last task run", "Check if the taskrunner is still running".
skill-author
Use when designing or extending skills under skills/. Owns the folder-per-skill convention with SKILL.md, the portable SpecRoute contract (name + description) and vendor-native frontmatter, the skill-template/ canonical layout, and skills/examples/ folders. Ensures skills are interactive parameterized workflows with a…
spec-reviewer
Use when reviewing a PRD, requirements/design/tasks triplet, implementation plan, or agent prompt for completeness before code work starts. Owns requirement coverage, acceptance criteria quality, task back-references, and unresolved open questions. Triggers - "review this spec", "audit the requirements", "check this…