tool-noise-guard SKILL.md skillA

tool-noise-guard from tmusser/ai-engineering-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tmusser/ai-engineering-skills/tool-noise-guard@git:20260724.f589327

Pins git:20260724.f589327 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tmusser/ai-engineering-skills
Path
skills/tool-noise-guard/SKILL.md
Versions recorded
1
Latest version
git:20260724.f589327, committed Jul 24, 2026
Size
6,233 bytes
Repository stars
6
License
MIT

Passive guardrail that compacts repetitive tool-result envelopes, preserves decision-relevant anchors and deltas, and suppresses redundant re-fetches without pretending prior context disappeared.

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

# Tool Noise Guard

## Purpose

Reduce the forward propagation of tool-call bloat during tool-heavy work.

**Compact forward, not backward.** This skill cannot remove raw tool output that the
runtime already injected into context. It prevents that cost from multiplying by
re-quoting, re-summarizing, and re-fetching the same low-value metadata on later turns.

Never trade required evidence for token savings.

## When to use

Optional passive guardrail. Once explicitly enabled for a tool-heavy task or session,
stay active until the user disables it or the task no longer uses tools.

Stay silent by default. Intervene behaviorally when one or more of these signals appear:

- successive tool results repeat the same wrapper, schema, or stable metadata
- a list/search response contains many fields but only a few affect the next decision
- the same resource is fetched or polled again without a concrete freshness reason
- a follow-up call can reuse an existing ID, cursor, path, or resource reference
- verbose tool envelopes are being copied into summaries, handoffs, or user-facing prose

Do not compact aggressively when exact raw payload shape is itself the evidence, when
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tmusser/ai-engineering-skills/tool-noise-guard@sha256:18a5eee73647e744

The line at the top of this page pins the label git:20260724.f589327, 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_wajx4wgc26ttmbhk.svg)](https://markdownregistry.com/a/art_wajx4wgc26ttmbhk)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 24, 2026.

versioncommittedcommitsizeaudit
git:20260724.f589327 latest2026-07-24 f589327 6,233 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 (6233 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

tmusser/ai-engineering-skills · 6 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wajx4wgc26ttmbhk
GET https://markdownregistry.com/api/v1/resolve?ref=tmusser/ai-engineering-skills/tool-noise-guard
GET https://markdownregistry.com/api/v1/blob/18a5eee73647e74411c799e5310b774b1fd7e40b8a4f5b83acace456c7717e80

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 tmusser/ai-engineering-skills

AGENTS.md AGENTS.md file
tmusser/ai-engineering-skills · AGENTS.md
git:20260723.bcffaf4 · audit A · 6 stars
analyze-mini SKILL.md skill
tmusser/ai-engineering-skills · skills/analyze-mini/SKILL.md · Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support…
git:20260727.5a2073a · audit A · 6 stars
bug-capture SKILL.md skill
tmusser/ai-engineering-skills · skills/bug-capture/SKILL.md · Preserve discovered bugs as BUGS.md entries.
git:20260518.0d37b7d · audit A · 6 stars
build-one SKILL.md skill
tmusser/ai-engineering-skills · skills/build-one/SKILL.md · Implement exactly one planned slice after scope is frozen, without exceeding the spec ceiling or carrying known…
git:20261101.bfc03f8 · audit A · 6 stars
ceremony-budget SKILL.md skill
tmusser/ai-engineering-skills · skills/ceremony-budget/SKILL.md · Choose the smallest workflow that still buys back enough attention and safety for the task.
git:20261005.a4c4424 · audit A · 6 stars
checklist-mini SKILL.md skill
tmusser/ai-engineering-skills · skills/checklist-mini/SKILL.md · Validate a mini-spec before planning.
git:20260518.0d37b7d · audit A · 6 stars
constitution-lite SKILL.md skill
tmusser/ai-engineering-skills · skills/constitution-lite/SKILL.md · Define a tiny set of stable, non-negotiable agent authority boundaries for repeated or delegated work without…
git:20260727.96471d7 · audit A · 6 stars
context-check SKILL.md skill
tmusser/ai-engineering-skills · skills/context-check/SKILL.md · Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps…
git:20260626.1692c35 · audit A · 6 stars
diagnose-loop SKILL.md skill
tmusser/ai-engineering-skills · skills/diagnose-loop/SKILL.md · Diagnose reproducible failures with hypothesis-driven fixes and bounded retries.
git:20260910.1199fd5 · audit A · 6 stars
eco-mode SKILL.md skill
tmusser/ai-engineering-skills · skills/eco-mode/SKILL.md · Keep a small, budgeted working context for low-cost model execution without weakening task contracts, required sources…
git:20261026.2efd117 · audit A · 6 stars
falsify-spec SKILL.md skill
tmusser/ai-engineering-skills · skills/falsify-spec/SKILL.md · Adversarially test a bounded SPEC.md for plausible wrong implementations that still pass its written acceptance…
git:20261020.30b4737 · audit A · 6 stars
grill-with-docs-lite SKILL.md skill
tmusser/ai-engineering-skills · skills/grill-with-docs-lite/SKILL.md · Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, using…
git:20261005.a4c4424 · audit A · 6 stars

Every file in tmusser/ai-engineering-skills

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