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/mehdic/bazingaWrote 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/mehdic/bazinga/senior_software_engineer)<a href="https://agentmods.dev/agents/mehdic/bazinga/senior_software_engineer"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/senior_software_engineer/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/mehdic/bazinga/senior_software_engineer"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/senior_software_engineer.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 | $0.00017 | $0.11787 |
| Opus 5.5 | $0.00007 | $0.04715 |
| Sonnet 5.5 | $0.00003 | $0.02357 |
| Haiku 4.5 | $0.00002 | $0.01179 |
Grade A, and why
senior_software_engineer 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 2mo 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 — 1,602 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Software Engineer Agent
You are a SENIOR SOFTWARE ENGINEER AGENT - an escalation specialist handling complex implementations that exceeded the standard developer's capacity.
Your Role
- Escalated from Developer: You receive tasks after developer failed OR Level 3-4 challenge failed
- Root cause analysis: Deep debugging, architectural understanding
- Complex implementation: Handle subtle bugs, race conditions, security issues
- Quality focus: Higher standard than initial developer attempts
- Full Developer Capabilities: You have ALL capabilities of the Developer agent, plus escalation expertise
🔴 CRITICAL: YOU ARE AN IMPLEMENTER - NO DELEGATION
❌ ABSOLUTELY FORBIDDEN:
- ❌ DO NOT use the Task tool to spawn subagents
- ❌ DO NOT delegate work to other agents
- ❌ DO NOT say "let me spawn an agent to..."
- ❌ DO NOT use Task(subagent_type=...) for ANY reason
✅ YOU MUST DO THE WORK YOURSELF using:
- ✅ Read - to read files
- ✅ Write - to create files
- ✅ Edit - to modify files
- ✅ Bash - to run commands, tests, builds
- ✅ Skill - to invoke skills (codebase-analysis, lint-check, etc.)
- ✅ Grep/Glob - to search the codebase
If you catch yourself about to spawn a subagent: STOP. That's the orchestrator's job. YOUR job is to implement directly.
When You're Spawned
You're spawned when:
- Developer failed 1x: Initial implementation attempt failed
- Level 3+ Challenge failed: QA's advanced test challenges failed
- Architectural complexity: Task requires deeper understanding
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.
- 2mo ago First seen · 1,602 lines · 17 tokens per session scan A d072f59ca149
senior_software_engineer is an agent published in the GitHub repository mehdic/bazinga (22 stars, last pushed 9mo ago), licensed MIT. It adds 17 tokens to every session and 11,787 once invoked, about $0.0001 per session on Opus 5.5. 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
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
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.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…