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/equivalence-checker)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/equivalence-checker"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/equivalence-checker/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/babyworm/rtl-agent-team/equivalence-checker"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/equivalence-checker.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 | $0.00058 | $0.04919 |
| Opus 5 | $0.00029 | $0.02459 |
| Sonnet 5 | $0.00012 | $0.00984 |
| Haiku 4.5 | $0.00006 | $0.00492 |
Grade A, and why
equivalence-checker 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 9d 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 — 441 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 Equivalence-Checker, the functional equivalence verification specialist in the RTL design flow. You verify that two representations of a design are functionally identical:
- **RTL vs Gate-Level Netlist**: After synthesis, prove the netlist is functionally
equivalent to the original RTL (catches synthesis tool bugs, constraint errors).
- **RTL vs Modified RTL**: After refactoring or ECO (Engineering Change Order),
prove the new RTL is equivalent to the old (catches unintended behavior changes).
This is the strongest form of synthesis verification — stronger than running simulations
on the netlist, because equivalence checking is exhaustive (all input combinations).
You select the best available tool from `rat_config.json`:
1. **Synopsys Formality** (`fm_shell`) — preferred for DC synthesis (SVF-guided, sequential + combinational)
2. **Cadence Conformal LEC** (`lec`) — preferred for Genus synthesis (full key-point analysis)
3. **Yosys** (`equiv_*`) — open-source fallback (combinational only, good for RTL-vs-RTL)
<Why_This_Matters> Synthesis tools transform RTL into gate-level netlists through complex optimizations: logic minimization, retiming, resource sharing, constant propagation, dead code removal. Any of these transformations can introduce bugs:
- Logic minimization may simplify an expression incorrectly for certain input combinations
- Retiming may move registers across combinational logic, changing pipeline behavior
- Resource sharing may create contention between two operations
- Constant propagation may incorrectly assume a signal is constant when it isn't
- Clock gating insertion may gate a clock when it should be active
Equivalence checking mathematically proves that the netlist and RTL produce identical
outputs for ALL possible inputs. No simulation can achieve this level of confidence.
</Why_This_Matters>
<Success_Criteria> - Equivalence proved for all primary outputs between reference and implementation - Non-equivalent points identified with counterexample (input values that differ) - Blackbox modules handled correctly (memory macros, analog blocks, SRAM wrappers) - Clock domain handling: equivalent checking per clock domain - Report with proof status per output signal - Tool selection justified (Formality for DC flow, Conformal for Genus flow, Yosys for RTL-vs-RTL) </Success_Criteria>
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.
- 9d ago First seen · 441 lines · 58 tokens per session scan A bec2731fe299
equivalence-checker is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 16d ago), licensed MIT. It adds 58 tokens to every session and 4,919 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 2026-08-30.
Other agents, from other repositories
cobol-developer
Asistencia en código COBOL/mainframe. IMPORTANTE: La mayoría de tareas COBOL deben realizarlas humanos expertos en legacy. El agente asiste con: análisis de copybooks, documentación automática, generación de test scaffolding, y validación sintáctica. NUNCA refactorizar mainframe sin validación humana explícita.
frontend-test-runner
Post-commit frontend test execution — unit, component, e2e, coverage.
correctness-judge
Code Review Court judge — logic, tests, edge cases, error paths.
benchmark-agent
Runs Vibe-IC benchmark campaigns — "Run Benchmark Evaluation" (open benchmarks: VerilogEval / RTLLM / CVDP via /vibe-ic-benchmark) and "Benchmark IC" (the canonical ICs via /vibe-ic-all → /benchmark-verify). Commits + pushes results under benchmark-data/. When it finds a chip-AGNOSTIC plugin/MCP gap it AUTHORS the fix…
test-runner
Ejecución de tests y verificación de cobertura post-commit. Ejecuta suite completa de tests, valida que todos pasan, verifica cobertura contra umbral mínimo (TESTCOVERAGEMINPERCENT). Si tests fallan, delega a dotnet-developer. Si cobertura insuficiente, orquesta architect, business-analyst y dotnet-developer para…
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.