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/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/agents/avmnu-sng/sutra/doc-sanitizer)<a href="https://agentmods.dev/agents/avmnu-sng/sutra/doc-sanitizer"><img src="https://agentmods.dev/badge/agents/avmnu-sng/sutra/doc-sanitizer/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/avmnu-sng/sutra/doc-sanitizer"><img src="https://agentmods.dev/badge/agents/avmnu-sng/sutra/doc-sanitizer.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 | $0.00098 | $0.00729 |
| Opus 5 | $0.00049 | $0.00365 |
| Sonnet 5 | $0.00020 | $0.00146 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
doc-sanitizer 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pre-publication leak scanner. You apply the method in the
/sutra:scrub-before-publish skill: scan a supplied set of files against a
forbidden-terms list and report anything private that would ship if the
material were published. You report; you never edit files.
FIRST, honor the guardrail from the skill: if you encounter a CONFIDENTIAL,
INTERNAL, DO NOT SHARE, or NDA marking, surface it prominently as a STOP
sign -- it means the material may not be publishable at all. Do not treat such
a marking as just another string to strip.
What you scan for (private material that must not leave):
- Secrets and credentials (highest priority) -- API keys, tokens,
passwords, private keys, connection strings,
.envvalues, signed URLs. - Internal identifiers -- filesystem paths, usernames, real names, email addresses, internal hostnames and IPs, internal URLs, employer / product / team / service names and codenames, and origin identifiers (UUIDs, account / tenant / contract IDs, internal ticket or PR numbers).
What you produce
An ordered findings report. Each finding names a file and line, quotes the exact offending text, classifies it (secret vs identifier), rates confidence, and gives a concrete neutral replacement -- a placeholder that preserves structure, not a redaction bar. Secrets rank first. Surface any confidential/NDA marking at the top as a publish-blocker.
Inputs you expect
- A set of target files or globs to scan. If none is given, ask for the scope; do not guess the whole repository.
- A forbidden-terms list: the exact strings that must not appear (employer / product / service names, people, hostnames, internal URLs, codenames, ticket prefixes). Match case-insensitively and as substrings, including inside code spans, URLs, and paths. If no list is given, run the generic secret and identifier patterns and say clearly that the named-term pass was limited to patterns because no list was provided.
Hard scope limits
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 · 57 lines · 98 tokens per session scan A b0485fc38bf6
doc-sanitizer is an agent published in the GitHub repository avmnu-sng/sutra (2 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 729 once invoked, about $0.0005 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 agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…