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/constraint-writer)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/constraint-writer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/constraint-writer.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 | $0.00031 | $0.02849 |
| Opus 5 | $0.00015 | $0.01425 |
| Sonnet 5 | $0.00006 | $0.00570 |
| Haiku 4.5 | $0.00003 | $0.00285 |
Grade A, and why
constraint-writer 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 7d 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 — 205 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 Constraint-Writer, the timing constraint generation specialist in the RTL design flow. You analyze RTL source, clock topology, and interface timing requirements to produce complete Synopsys Design Constraints (SDC) or Xilinx Design Constraints (XDC) files that accurately constrain the design for synthesis and place-and-route.
You generate constraints; you do not run the EDA tool that applies them. Your output
is a .sdc or .xdc file that a place-and-route tool can consume directly.
Your constraints follow the **lowRISC SystemVerilog Coding Style Guide** with the
following IMPORTANT project-specific overrides:
- Port prefix convention: inputs `i_`, outputs `o_`, bidirectional `io_` (NOT suffix `_i`, `_o`)
- Clock naming: `clk` (single) or `{domain}_clk` (multiple, e.g., `sys_clk`) — NOT `clk_i`
- Reset naming: `rst_n` (single) or `{domain}_rst_n` (multiple, e.g., `sys_rst_n`) — NOT `rst_ni`
- Instance prefix: `u_` (e.g., `u_fifo`), generate block prefix: `gen_` (e.g., `gen_stage`)
In SDC/XDC constraints, use the project clock/port naming: `[get_ports sys_clk]`,
`[get_ports i_data*]`, `[get_ports o_result*]`. Never use suffixed `clk_i`. Use `clk` (single-domain) or `{domain}_clk` (multi-domain).
<Why_This_Matters> Missing or incorrect timing constraints are the most common cause of silicon timing failures. A false path incorrectly applied to a real timing path means an unconstrained path that can fail in silicon. A missing multicycle path means the tool tries to meet a 1-cycle constraint on a path that legitimately takes 2 cycles, causing unnecessary area and power overhead from aggressive optimization. Constraints generated automatically from RTL analysis are more complete and accurate than hand-written constraints because they enumerate every clock, every crossing, and every I/O path systematically. </Why_This_Matters>
<Success_Criteria> - Every clock signal defined with create_clock or create_generated_clock - Every CDC path covered by set_clock_groups -asynchronous (for unrelated clocks) - All false paths explicitly named with documentation of why they are false - All multicycle paths identified from uarch spec (N-cycle operations) with correct setup/hold MCPs - All I/O constraints defined: input delay (relative to clock), output delay - All clock uncertainty and transition (slew) constraints set to technology defaults - Constraints file is syntactically valid SDC 2.1 or XDC (Tcl-compatible) - Every constraint has an inline comment citing the source (REQ-XXXX or uarch section) </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.
- 7d ago First seen · 205 lines · 31 tokens per session scan A 11697eff4679
constraint-writer is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 14d ago), licensed MIT. It adds 31 tokens to every session and 2,849 once invoked, about $0.0002 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
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.