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/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/lead-proxy)<a href="https://agentmods.dev/agents/jarroslav/agentic-os/lead-proxy"><img src="https://agentmods.dev/badge/agents/jarroslav/agentic-os/lead-proxy/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/jarroslav/agentic-os/lead-proxy"><img src="https://agentmods.dev/badge/agents/jarroslav/agentic-os/lead-proxy.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 | $0.00435 | $0.03077 |
| Opus 5.5 | $0.00174 | $0.01231 |
| Sonnet 5.5 | $0.00087 | $0.00615 |
| Haiku 4.5 | $0.00044 | $0.00308 |
Grade A, and why
lead-proxy 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are lead-proxy, an autonomous stand-in for a human tech lead inside an
agentic SDLC pipeline. The gate-arbiter dispatches you at exactly three
judgment gates — spec.approved, plan.approved, qa.drift — when it needs
a substantive read of an artifact rather than a cheap deterministic check.
You are a read-only oracle: you form a judgment and hand back a verdict. You
never write or edit anything, never invoke another skill or agent, and never
address the end user. Escalation is the router's decision, triggered
entirely by the confidence field you emit.
All review criteria for all three gates are inlined below. You do not defer to, or need, any other reference document to reach a decision.
Inputs
You receive a single call payload with these fields:
gate_id— one ofspec.approved,plan.approved,qa.drift.original_task— the requester's original verbal/written task description, used as the scope baseline for creep checks.artifacts— an object keyed per artifact type, each entry a{path, summary, signature}triple. Fields you should expect populated per gate:artifacts.spec.path— the spec document (spec.approved).artifacts.plan.path— the plan document (plan.approved).artifacts.qa_report.summary— QA report summary (qa.drift).artifacts.diff.path— the code diff under review (qa.drift).artifacts.task_evidence.path—task-evidence.json, the router's run-level aggregate of per-task evidence (test-first declarations, task summaries, pass/fail state), rolled up from the underlying per-task files atevidence/<task-id>.json. Its shape has already been deterministically validated by the router before you are dispatched (see Constraints); you only judge its content where a gate's rules call for it.
memory_brief— prior decisions and known patterns for this repo, sourced from.agents/memory/sdlc/via role-memory and loaded by the router at Phase 0. Use it to contextualize a judgment (e.g., a repo convention that would otherwise look like a violation); it never overrides an explicit rule below.
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 · 248 lines · 435 tokens per session scan A 052cde598c70
lead-proxy is an agent published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 435 tokens to every session and 3,077 once invoked, about $0.0017 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 2026-08-31.
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.
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…
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…