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.
npx skills add chipweaver/veripower --skill lint-cdcgit clone --depth 1 https://github.com/chipweaver/veripowerWrote 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/skills/chipweaver/veripower/lint-cdc)<a href="https://agentmods.dev/skills/chipweaver/veripower/lint-cdc"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/lint-cdc/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/skills/chipweaver/veripower/lint-cdc"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/lint-cdc.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 | $0.00028 | $0.00615 |
| Opus 5.5 | $0.00011 | $0.00246 |
| Sonnet 5.5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
lint-cdc 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 1mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint and CDC
Assess the RTL against the task's lint and CDC requirements. Read dispatch.json, original intent,
requirements, RTL, constraint annotations and specification SGDC. Use carried evidence when its
implementation, setup and scope still apply; choose the checks the current task needs.
Write under {workdir}; upstream inputs remain read-only. The framework carries published setup
and reports into this directory, without the old verdict. Keep useful analysis in evidence/.
Prepare and check
<skill> is this skill's directory:
python3 <skill>/scripts/lintcdc/__main__.py bootstrap --workdir {workdir}
Bootstrap installs missing setup without overwriting authored files and refreshes the file list
and generated SGDC. constraint-annotations.json
supplies synchronizer, reset, case-analysis and quasi-static declarations. Check inherited
scripts/local.sgdc and scripts/waiver.tcl against the current design. Correct invalid input
declarations at their source.
Run make lint, make cdc, or make all from the prepared workdir; all shares elaboration.
The entrypoint withdraws the selected check's old summaries before execution. Wait for completion,
read the reports and inspect both reported and waived violations. The reports include native
waiver details when messages were waived. Record the basis in -comment, with evidence references
where needed; assess it against the requirements, including whether limits apply before or after waivers.
Repair local setup errors and rerun the affected checks.
Judge and close
python3 <skill>/scripts/lintcdc/__main__.py finalize --workdir {workdir} \
[--requirements '[{"id":"R-1","met":true,"actual":"observed result","measured":"report and scope"}]'] \
[--fail-reason "unresolved cause"] [--fix-owner <rule>]
Declare a judgment for every lint-cdc requirement using the reports and the actual waiver policy.
finalize reads lint-violations.json and cdc-violations.json; it does not judge waiver reasoning.
Use --fail-reason for unjustified waivers or invalid/incomplete checks, even when counts are zero. Name
the repair owner from the defect, including this stage for its own setup; do not infer ownership
from the path of an error. Attribution guidance describes the constraint sources to check.
Acceptance changes follow the user's actual authorization.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/attribution-rules.md 1.1 KB
- references/result.schema.json 3.6 KB
- scripts/lintcdc/__init__.py 0 B runs code
- scripts/lintcdc/__main__.py 2.8 KB runs code
- scripts/lintcdc/bootstrap.py 9.4 KB runs code
- scripts/lintcdc/requirements.py 3.0 KB runs code
- scripts/lintcdc/result.py 6.5 KB runs code
- templates/env.sh 700 B runs code
- templates/Makefile 2.9 KB
- templates/README.md 1.0 KB
- templates/scripts/collect_report.py 14 KB runs code
- templates/scripts/local.sgdc 1.0 KB
- templates/scripts/run_spyglass.sh 1.3 KB runs code
- templates/scripts/run.tcl 2.7 KB
- templates/scripts/spyglass_lint.prj 2.0 KB
- templates/scripts/waiver.tcl 1.2 KB
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.
- 1mo ago Changed · -94 lines · -12 tokens per session f794203e0044
- 1mo ago Changed · -2 lines 2e875398a6cf
- 1mo ago Changed · +5 lines 5fb378673fd6
- 1mo ago First seen · 144 lines · 40 tokens per session scan A 130ba506d9e1
lint-cdc is a skill published in the GitHub repository chipweaver/veripower (10 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 615 once invoked, about $0.0001 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 skills, from other repositories
vdebug
Trace failing signals through the RTL hierarchy, classify root cause, and write a debug report per issue — no fix is proposed.
vdesign
Generate a design proposal, documentation, and RTL backbone from a requirement file.
varch
Decompose an IP requirement into submodules, define interfaces, and generate an architecture document plus per-module requirement files and a top-level skeleton.
vfill
Implement Verilog code from an approved design proposal, then lint and simulate.
vflow
Scan project state to determine phase completion, write flowstatus.md, and orchestrate the full RTL design flow from architecture to documentation.
vsynth
Synthesize a Verilog module or full IP with Vivado and report resource utilization, Fmax, and power.