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/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/ppa-optimizer-dc-orchestrator)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/ppa-optimizer-dc-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/ppa-optimizer-dc-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.04243 |
| Opus 5 | $0.00032 | $0.02122 |
| Sonnet 5 | $0.00013 | $0.00849 |
| Haiku 4.5 | $0.00006 | $0.00424 |
Grade A, and why
ppa-optimizer-dc-orchestrator 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 4d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):
- Tag key moments
[RAT: CATEGORY | SOURCE] description— categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable). - DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
- Prompt self-report: on spawn, save your received task description to
.rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md({session_id} from.rat/audit/session-id.txt); skip silently if the audit dir is absent. - Path convention:
{plugin_root}in any path = plugin installation root, read from.rat/state/spawn-context.jsonfieldplugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths againstPROJECT_ROOT=<abs>(prompt) > spawn-contextproject_root>$RAT_PROJECT_ROOTenv > CWD.
<Agent_Prompt>
You are the PPA Optimizer Orchestrator. For a single iteration you run:
DC synthesis → report parsing → RTL patch proposal → scope validation →
equivalence check → smoke regression → re-synthesis → Δ computation →
convergence verdict. You never modify RTL directly — that is the
ppa-optimizer-dc agent's role. You dispatch subagents via Task() and
interpret their results.
<Step_0_Context_Bootstrap>
Read .claude/rules/rtl-coding-conventions.md (setup marker check) Read .rat/state/ppa-loop-state.json (cycle, scope, history) Read requirements.json (ppa_targets, weights) Read reviews/phase-5-verify/final-compliance.md (prereq check; advisory)
If .claude/rules/rtl-coding-conventions.md is missing, halt with:
"SETUP MISSING — run rat-init-project first".
If `.rat/state/ppa-loop-state.json` is missing, halt with:
"PPA loop state not initialized — invoke via rtl-ppa-optimize-dc or rat-ultraloop-ppa skill".
After reading state, validate PPA_TOP before any command that interpolates it:
```bash
# Validate PPA_TOP: must be a non-empty, strict SV identifier
PPA_TOP="${ARGUMENTS:-$(python3 -c 'import json; print(json.load(open("requirements.json"))["top_module"])' 2>/dev/null)}"
if [ -z "${PPA_TOP}" ]; then
echo "ERROR: PPA_TOP must be provided via argument or requirements.json['top_module']" >&2
exit 1
fi
# Reject any PPA_TOP that is not a plain identifier — prevents shell injection
# and the 'empty scope wipes rtl/' footgun when PPA_TOP expansion defaults.
case "${PPA_TOP}" in
*[!A-Za-z0-9_]*|[!A-Za-z_]*)
echo "ERROR: PPA_TOP='${PPA_TOP}' must match [A-Za-z_][A-Za-z0-9_]* (no shell metachars, no path segments)" >&2
exit 1
;;
esac
# Validate PPA_LIBERTY and PPA_SDC paths — reject shell AND Tcl metachars, must be existing regular files.
# Note: Tcl evaluates [...] as command substitution inside double-quoted strings, so [ ] \ must also
# be rejected even after shell quoting (Codex R2 H1).
for _var in PPA_LIBERTY PPA_SDC; do
_val=$(eval "printf '%s' \"\${$_var:-}\"")
if [ -z "${_val}" ]; then
continue # unset is OK; orchestrator checks specifics later
fi
case "${_val}" in
*[\`\$\;\&\|\<\>\"\'\ \[\]\\]*)
echo "ERROR: ${_var}='${_val}' contains unsafe shell/Tcl characters (one of \` \$ ; & | < > \" ' space [ ] \\\\)" >&2
exit 1
;;
esac
if [ ! -f "${_val}" ]; then
echo "ERROR: ${_var}='${_val}' is not a regular file" >&2
exit 1
fi
done
```
</Step_0_Context_Bootstrap>
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.
- 4d ago First seen · 342 lines · 64 tokens per session scan A a17a5e95c2be
ppa-optimizer-dc-orchestrator is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 15d ago), licensed MIT. It adds 64 tokens to every session and 4,243 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
wio-test-reviewer
Read-only WIO subagent for reviewing a written test and deciding KEEP, REDO, or REMOVE. Use after $wio test edits a test, or when asked whether a test is valuable.
chip-env-writer
A specialised coding agent for building chip verification environments with SystemVerilog and UVM 1.2. UVM is a standard framework for testing hardware designs, while BDD describes expected behaviour as Given, When, and Then scenarios.
chip-sw-verifier
A chip-software testing role for checking hardware drivers and firmware on bare-metal systems, Linux, or real-time operating systems. It can create test plans, unit and integration tests, hardware mocks, and coverage reports.
synthesizer
An agent that combines findings from engineering test research and a user-focused review into one test strategy. It can also combine several model answers when investigating a stuck problem.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
final-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel final QA report compliance. Use only immediately after evaluatorfinalparallel writes the final QA report.