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 NOMARJ/sigil --skill silence-auditgit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/silence-audit)<a href="https://agentmods.dev/skills/nomarj/sigil/silence-audit"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/silence-audit/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/nomarj/sigil/silence-audit"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/silence-audit.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 | $0.00075 | $0.01116 |
| Opus 5.5 | $0.00030 | $0.00446 |
| Sonnet 5.5 | $0.00015 | $0.00223 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
silence-audit 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Silence Audit — Who Is Missing and Why
Purpose
Public internet evidence systematically over-represents certain populations and under-represents others. This skill makes that bias visible. It does not eliminate it — it names it, assesses its impact, and proposes mitigation.
A persona panel without a Silence Audit will confidently represent the internet's majority voice and mistake it for the whole picture. That is the opposite of empathy.
When to Run
- Mandatory: After Step 3 (persona construction) in every full DISCOVER run
- Optional: Standalone via
/silence-auditto check existing evidence - Cannot be skipped during full DISCOVER
The Protocol
1. Identify Evidence Sources Present
List every source type used in the persona panel's evidence chains:
- Product reviews
- Forum discussions
- Support threads
- Social media
- Published interviews
- Job postings
- Academic/industry research
- Government/census data
- Analytics data
- Direct user conversations
2. Check for Systematic Over-Representation
These groups dominate public internet evidence:
| Over-Represented | Why |
|---|---|
| English speakers | Internet content skews English |
| Tech-literate users | They write reviews, post on forums |
| Affluent consumers | They buy products worth reviewing |
| Vocal extremes | Strong opinions get posted; mild ones don't |
| Younger demographics | Higher social media activity |
| Urban populations | Better internet access, more digital services |
Ask: Does my persona panel disproportionately reflect these groups?
3. Check for Systematic Under-Representation
These groups are typically absent from public internet evidence:
| Under-Represented | Why |
|---|---|
| Non-English speakers | Content in other languages wasn't searched |
| Older adults (65+) | Lower digital presence, fewer reviews |
| Low-income users | Don't buy products to review, less digital access |
| People with disabilities | Unless product targets accessibility specifically |
| Regulated industry users | Can't discuss work publicly (finance, defence, healthcare) |
| Silent satisfied | Use the product daily, never post about it |
| Silent churn | Tried it, left, said nothing |
| Rural populations | Less digital infrastructure, fewer online communities |
| Non-binary/minority groups | Under-represented in training data and review platforms |
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 First seen · 128 lines · 75 tokens per session scan A dbed0c993a5b
silence-audit is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,116 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
sftp-cc
A natural-language SFTP tool for uploading local project files to a remote server. SFTP is a secure way to transfer files, and this tool supports incremental uploads, private-key binding, and permission fixes.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
thread-list
Inspect or change the sidebar thread list's layout preferences: organization mode, sort, section order, hidden groups, collapsed groups, and thread row actions.
workflows
Author or run durable BB workflows when the user requests workflow execution or multi-agent orchestration.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
url
Fetch and extract text from web URLs.