dos-witness-claim

dos-witness-claim is a skill for Claude Code from anthony-chaudhary/dos-kernel. It costs 47 tokens per session (3,578 once invoked), scanned A, original, MIT.

A procedure for independently checking claims made by one coding agent before another agent relies on them. A read-back means verifying the actual file, message, API result, or system state rather than trusting the report alone.

In plain words
What is it for?
Use it at parallel-work, pipeline, and synthesis checkpoints to verify files, records, messages, or other claimed changes before continuing.
Why use it?
It prevents unverified work from being treated as complete, especially when several agents or workflow stages are involved. Only effects confirmed by an independent check are carried forward.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the dos-kernel plugin — 18 skills, 3 hooks, 1 MCP server shipped together

Good fit Use it at parallel-work, pipeline, and synthesis checkpoints to verify files, records, messages, or other claimed changes before continuing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthony-chaudhary/dos-kernel/dos-witness-claim
Install

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.

Any agent
npx skills add anthony-chaudhary/dos-kernel --skill dos-witness-claim
Clone the repo
git clone --depth 1 https://github.com/anthony-chaudhary/dos-kernel

Made for: Claude Code.

Or install dos-kernel, the plugin that ships this one along with the rest of its 18 skills, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for dos-witness-claim

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthony-chaudhary/dos-kernel/dos-witness-claim/github.svg)](https://agentmods.dev/skills/anthony-chaudhary/dos-kernel/dos-witness-claim)
Your own site
<a href="https://agentmods.dev/skills/anthony-chaudhary/dos-kernel/dos-witness-claim"><img src="https://agentmods.dev/badge/skills/anthony-chaudhary/dos-kernel/dos-witness-claim/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.

agentmods 80×15 button for dos-witness-claim

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthony-chaudhary/dos-kernel/dos-witness-claim"><img src="https://agentmods.dev/badge/skills/anthony-chaudhary/dos-kernel/dos-witness-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,578 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.03578
Opus 5 $0.00023 $0.01789
Sonnet 5 $0.00009 $0.00716
Haiku 4.5 $0.00005 $0.00358

Measured 12d ago against content hash bfe3bae25f09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dos-witness-claim 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 12d 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.

claude-plugin/skills/dos-witness-claim/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dos-witness-claim — fold the witnessed effect, never the narrated one

This is the screenplay for the one move the whole substrate exists to make: when a subagent hands you a result, the result is a claim, not a fact. A claim re-narrating the agent's own work is consistency, not grounding (docs/138). Belief is earned only by a read-back whose byte-author is not the judged agent (a fresh GET, a git existence check, an OS exit code, a state diff). This skill never decides ground truth itself — it shells dos verbs and reads the verdict. The kernel decides; the skill narrates.

The shape is domain-free: discover the layout → classify the claim type → witness it on a non-forgeable rung → fold ONLY confirmed. The policy (which lanes, which plan grammar, where state lives) is data the screenplay reads from dos doctor --json, never literals it hardcodes.

The seed-2 payoff. This makes the worker's MODEL TIER irrelevant to trust. A weak worker and a strong worker face the SAME witness gate: both have their claimed effect re-read from a surface they did not author. A confident, fluent, frontier-strength narration of a success the world does not corroborate is exactly the silent fail this gate catches (docs/177) — and a weak worker that actually shipped the effect passes it. Distrust is aimed at the byte-author of the evidence, not at the worker's eloquence.

Inputs

  • A set of subagent results to fold (return strings + their transcript paths), e.g. the children of a parallel() barrier or a pipeline() stage. A result is the thing you are tempted to interpolate directly (${result}) — don't.
  • For each result, the effect it claims (a (plan, phase), a created file path, a DB row key, a sent-message id). If the worker emitted no checkable effect, that is a real outcome (NO_CLAIM), not a pass — see Step 2.

Step 0 — Discover the workspace layout (one call)

Run the doctor verb and read the result. This is the WCR on-ramp: every path/lane/exit-code below comes from here, never a literal.

Read the full file on GitHub · 252 lines

Changes

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.

  1. 12d ago First seen · 252 lines · 47 tokens per session scan A bfe3bae25f09

Subscribe to this mod's changes

dos-witness-claim is a skill published in the GitHub repository anthony-chaudhary/dos-kernel (19 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 3,578 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.