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 avmnu-sng/sutra --skill scrub-before-publishgit clone --depth 1 https://github.com/avmnu-sng/sutraWrote 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/avmnu-sng/sutra/scrub-before-publish)<a href="https://agentmods.dev/skills/avmnu-sng/sutra/scrub-before-publish"><img src="https://agentmods.dev/badge/skills/avmnu-sng/sutra/scrub-before-publish/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/avmnu-sng/sutra/scrub-before-publish"><img src="https://agentmods.dev/badge/skills/avmnu-sng/sutra/scrub-before-publish.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 | $0.00037 | $0.00994 |
| Opus 5 | $0.00018 | $0.00497 |
| Sonnet 5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
scrub-before-publish 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrub before publish
Before you publish material you have the right to publish -- open-sourcing your own repo, posting a sample, sharing a runbook -- remove the private details first. This is a security and privacy pass, not a rewrite: you keep the authorship, the license, and the substance; you strip the secrets and internal identifiers that should never leave the building.
Guardrail first: only publish what is yours to publish
This skill is for material you are authorized to release. It is NOT a way to work around a restriction.
- A
CONFIDENTIAL,INTERNAL,DO NOT SHARE, or NDA marking is a STOP SIGN, not a line to delete. If you find one, do not publish the material and do not strip the label -- get authorization or leave it internal. - If the material belongs to an employer, a customer, or someone else, or you are unsure you have the right to release it, stop and confirm before going further.
- Scrubbing removes secrets from material you MAY publish. It is never a tool for laundering material you may not.
What to remove
Search for and replace every private referent. Secrets are the highest priority -- a leaked credential is an incident, not a nit.
- Secrets and credentials -- API keys, tokens, passwords, private keys,
connection strings,
.envvalues, signed URLs. If one ever reaches a public commit it must be rotated, so catch it before, not after. - Absolute machine paths --
/Users/<name>/...,/home/<name>/...,C:\Users\.... Replace with a relative or generic path (./config,/path/to/project). - Usernames, handles, and personal names.
- Internal hostnames and IPs -- laptop names,
*.internal,*.corp, staging boxes, and private v4/v6 ranges. - Internal URLs -- wikis, dashboards, issue trackers, artifact registries, short links.
- Employer, customer, product, and service names -- including codenames and insider shorthand. Replace with a neutral role name ("a backend event service", "the image-upload endpoint").
- Email addresses.
- Account, tenant, and contract IDs; UUIDs -- even expired or example-looking ones; a real-shaped ID invites a probe.
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.
- 11d ago First seen · 89 lines · 37 tokens per session scan A 6ae381ed22df
scrub-before-publish is a skill published in the GitHub repository avmnu-sng/sutra (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 994 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 2026-08-31.
Other skills, from other repositories
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
memstack-deployment-domain-ssl
Use this skill when the user says 'setup domain', 'configure DNS', 'SSL certificate', 'domain-ssl', 'custom domain', 'HTTPS setup', or needs to configure DNS records, SSL certificates, and custom domains for any hosting provider. Do NOT use for full deployment workflows.
memstack-development-refactor-planner
Use this skill when the user says 'refactor', 'refactoring plan', 'code cleanup', 'reduce duplication', 'simplify code', 'tech debt', 'god class', 'tight coupling', or needs to systematically improve existing code. Identifies targets, assesses risk, and builds incremental execution plans. Do NOT use for writing new…
memstack-product-feedback-analyzer
Use this skill when the user says 'analyze feedback', 'feedback analysis', 'what are customers asking for', or has support tickets, reviews, or survey data to categorize, score, and prioritize into actionable reports. Do NOT use for competitor analysis or market research.
memstack-seo-meta-tag-optimizer
Use this skill when the user says 'meta tags', 'title tag', 'meta description', 'optimize meta', 'SERP preview', or needs to write or optimize HTML meta tags for better search visibility and click-through rates. Do NOT use for schema markup or full site audits.
familiar
Use when the user says 'dispatch', 'send familiar', 'split task', or needs work split across parallel CC sessions.