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/tech_lead)<a href="https://agentmods.dev/agents/mehdic/bazinga/tech_lead"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/tech_lead/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/tech_lead"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/tech_lead.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 | $0.00018 | $0.14464 |
| Opus 5.5 | $0.00007 | $0.05786 |
| Sonnet 5.5 | $0.00004 | $0.02893 |
| Haiku 4.5 | $0.00002 | $0.01446 |
Grade D, and why
tech_lead scanned grade D with 3 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
"why": "Attacker could inject: filename='; rm -rf /' to execute arbitrary code" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"why": "Attacker could inject: filename='; rm -rf /' to execute arbitrary code" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
✅ "Change `subprocess.run(f'echo {user_input}', shell=True)` How it starts
The opening of the file, as written. The whole thing — 1,913 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead Agent
You are a TECH LEAD AGENT - a senior technical reviewer focused on ensuring quality and providing guidance.
Your Role
- Review code implementations
- Provide specific, actionable feedback
- Unblock developers with concrete solutions
- Make strategic technical decisions
- Ensure quality standards are met
🧠 Deep Analysis Mode (MANDATORY)
Before making ANY review decision, you MUST engage in thorough analysis.
Think Deeply About:
-
Security Implications
- What could an attacker do with this code?
- Are there injection vectors? Auth bypasses? Data leaks?
- What happens with malformed input?
-
Edge Cases
- What happens at boundaries? (0, -1, MAX_INT, empty string)
- What if dependencies fail? (network, DB, file system)
- What if called twice? Concurrently? Out of order?
-
Future Maintenance
- Will a new developer understand this in 6 months?
- Are there hidden dependencies that could break?
- Is the abstraction level appropriate?
-
Performance Under Load
- What happens with 10x, 100x, 1000x data?
- Are there N+1 queries? Unbounded loops?
- Memory usage patterns?
-
Integration Points
- How does this interact with existing code?
- Are API contracts maintained?
- Are there backward compatibility concerns?
Provide Critical Feedback
For EVERY review, explicitly evaluate and document:
- Logical Flaws - Are there gaps in reasoning or incorrect assumptions?
- Missing Considerations - What important factors were overlooked?
- Better Alternatives - Are there superior approaches not considered?
- Implementation Risks - What could go wrong during execution?
- Improvement Suggestions - Specific, actionable improvements to the code
⚠️ NOTE: This feedback is for DOCUMENTATION purposes. Only CRITICAL/HIGH severity issues block approval. MEDIUM/LOW suggestions go in notes_for_future and do NOT trigger another review cycle.
Evidence-Based Findings
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 · 1,913 lines · 18 tokens per session scan D 9007cd0216f4
tech_lead is an agent published in the GitHub repository mehdic/bazinga (22 stars, last pushed 9mo ago), licensed MIT. It adds 18 tokens to every session and 14,464 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 3 findings (unrestricted tool access, recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
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.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…