task-framing-claims-need-subagent-grep-verify SKILL.md skillA

task-framing-claims-need-subagent-grep-verify from wan-huiyan/agent-traffic-control is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wan-huiyan/agent-traffic-control/task-framing-claims-need-subagent-grep-verify@v1.0.1

Pins v1.0.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wan-huiyan/agent-traffic-control
Path
plugins/agent-traffic-control/skills/task-framing-claims-need-subagent-grep-verify/SKILL.md
Versions recorded
5
Latest version
v1.0.1, committed Aug 11, 2026
First version recorded
May 29, 2026
Size
9,733 bytes
Repository stars
3
License
MIT

When dispatching a sub-agent (Agent / Task) to WRITE content that cross-references existing code paths, explicitly grant + expect grep-driven correction of the dispatcher's task-framing claims. Use when: (1) your prompt to a sub-agent asserts facts about what an existing codebase contains ("X is NOT in v6.1", "Y is already implemented at module Z", "feature F handles case G"); (2) the sub-agent will produce a document, analysis, or design that consumers will treat as authoritative; (3) the…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Task-framing claims need sub-agent grep-verify

## Problem

You dispatch a sub-agent to write content (analysis doc, design doc,
implementation plan, code review summary) that needs to cross-reference
existing code paths. To give the sub-agent a head start, you assert facts
in the prompt about what's currently in the codebase:

- "Feature X is NOT in v6.1's training pipeline; the v7 implication is to
  add it as a categorical feature"
- "Module Y already implements caching at line ~120"
- "The current handler doesn't support multipart uploads"

If any of those framing claims are wrong, the sub-agent has two failure
modes — both bad:

1. **Faithful reproduction.** The sub-agent treats your prompt as ground
   truth, doesn't grep to verify, and produces a doc with the wrong
   premise baked in. Downstream readers can't tell the doc was based on
   a faulty premise.

2. **Silent substitution.** The sub-agent greps, finds you wrong, and
   quietly substitutes its own (correct) view — but doesn't flag the
   contradiction. You think your prompt was correct because the doc
   reads sensibly; the discrepancy with your mental model never surfaces.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wan-huiyan/agent-traffic-control/task-framing-claims-need-subagent-grep-verify@sha256:9f4f663b54da8b1a

The line at the top of this page pins the label v1.0.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_y6iismqqfis2lk2s.svg)](https://markdownregistry.com/a/art_y6iismqqfis2lk2s)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 29, 2026 and Aug 11, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
v1.0.1 latest2026-08-11 f274e4b 9,733 BA view · diff
v1.0.12026-08-05 ef4b211 9,783 BA view · diff
v1.0.02026-07-08 b0f0d02 9,784 BA view · diff
v1.0.02026-07-08 f1254dd 9,781 BA view · diff
v1.0.02026-05-29 059688a 9,750 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9733 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wan-huiyan/agent-traffic-control · 3 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_y6iismqqfis2lk2s
GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/task-framing-claims-need-subagent-grep-verify
GET https://markdownregistry.com/api/v1/blob/9f4f663b54da8b1a7ed6846eaac487e481fd962b2336be0bcd6dfb05061e6c2f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wan-huiyan/agent-traffic-control

DESIGN.md@plugins/agent-traffic-control/hooks/resume-gate DESIGN.md file
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/hooks/resume-gate/DESIGN.md
git:20260812.d9a22d6 · audit A · 3 stars
agent-refusal-with-evidence-beats-literal-compliance SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/agent-refusal-with-evidence-beats-literal-compliance/SKILL.md · A dispatched agent that does exactly what you asked can ship a defect you would have stopped yourself, because it can…
v1.0.0 · audit A · 3 stars
async-doc-hook-autodocs-worktree-locks-branch-checkout SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/async-doc-hook-autodocs-worktree-locks-branch-checkout/SKILL.md · Fix for `git checkout <branch>` failing with `fatal: '<branch>' is already used by worktree at '.../autodocs-<name>'`…
v1.0.0 · audit A · 3 stars
async-post-commit-hook-commit-orphaned-by-squash-merge SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/async-post-commit-hook-commit-orphaned-by-squash-merge/SKILL.md · In a repo with an ASYNC/background post-commit hook (one that fires after a commit and creates its OWN follow-up commit…
v1.0.0 · audit A · 3 stars
auto-merge-rearms-while-agent-live-kill-then-disarm-verify SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/auto-merge-rearms-while-agent-live-kill-then-disarm-verify/SKILL.md · Disarming auto-merge on a PR whose agent is still running does not hold it — the agent re-arms within minutes and the…
v1.0.0 · audit A · 3 stars
batch-member-cites-a-path-only-a-non-member-adds SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/batch-member-cites-a-path-only-a-non-member-adds/SKILL.md · You wrote something correct that the default reader cannot reach: a batch member citing a path only a NON-member adds…
v1.1.0 · audit A · 3 stars
batch-merge-subject-is-not-evidence-a-member-landed SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/batch-merge-subject-is-not-evidence-a-member-landed/SKILL.md · You are about to close, delete the branch of, or mark as landed a pull request because a batch, roll-up or merge-train…
v1.0.0 · audit A · 3 stars
ci-leg-skipping-moves-minutes-it-does-not-remove-them SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/ci-leg-skipping-moves-minutes-it-does-not-remove-them/SKILL.md · You are about to propose, price or approve a CI cost saving that works by making a job or matrix leg SKIP on pull…
v1.0.0 · audit A · 3 stars
cjk-structured-llm-output-truncates-json-needs-2x-tokens SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/cjk-structured-llm-output-truncates-json-needs-2x-tokens/SKILL.md · When generating LONG Chinese/Japanese/Korean (CJK) STRUCTURED output (a big JSON report, a multi-section document) from…
v1.0.0 · audit A · 3 stars
claude-code-projects-jsonl-worktree-fanout SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/claude-code-projects-jsonl-worktree-fanout/SKILL.md · Find a prior session's transcript that `~/.claude/projects/<project>/` does not hold: each git worktree gets its own…
v1.0.0 · audit A · 3 stars
clean-merge-lands-line-guard-on-a-value-neither-branch-predicted SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/clean-merge-lands-line-guard-on-a-value-neither-branch-predicted/SKILL.md · Two branches each contain a guard, test or document that pins a line NUMBER in a third file, each side correctly…
v1.0.0 · audit A · 3 stars
code-review-subagent-fabricates-specifics-to-inflate-severity SKILL.md skill
wan-huiyan/agent-traffic-control · plugins/agent-traffic-control/skills/code-review-subagent-fabricates-specifics-to-inflate-severity/SKILL.md · When a code-review subagent (voltagent-qa-sec, opus-tier reviewer, code-reviewer, etc.) reports a HIGH or BLOCKING…
v1.0.0 · audit A · 3 stars

Every file in wan-huiyan/agent-traffic-control

Browse by kind, by grade A, or by owner.