Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Tool Restraint · archive228 | DecimalAI

agent toolingby archive228

Tool Restraint

archive228/tool-restraint

Source archive228/loopkit ↗License MIT

Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load.

SkillScore88Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 22 of 25 test cases with the skill, and 13 of 25 without it.

Without skill52%

With skill88%

Checks it passed that the model alone missed

advises disabling inactive tool servers
advises using official servers for credentialed tools
recommends enabling only tools needed for active tasks

and 10 more in the full report

9 fixed13 passed either way3 still failing0 broke

Pass-rate lift: +36 pp
Tokens: -31%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 25 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/archive228-tool-restraint/SKILL.md https://app.decimal.ai/s/archive228-tool-restraint/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-tool-restraint, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/archive228-tool-restraint/ and pins it in .decimal/skills.lock

decimalai skills add archive228-tool-restraint

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-tool-restraint/SKILL.md https://app.decimal.ai/s/archive228-tool-restraint/SKILL.md

Raw file: /s/archive228-tool-restraint/SKILL.md ↗ · machine-readable summary at /s/archive228-tool-restraint.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We are adding a Git MCP server that allows an agent to push code commits and push to remote branches. What mandatory logging measure must be implemented before activating write features?

What was checked, without and with the skill
Checked	Without skill	With skill
requires adding a hook that logs every call prior to enabling write capabilities	Missed	Passed

case-20 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

Tool Restraint

Loading an agent with 14 MCP servers "just in case" makes it slower and dumber, not more capable — tool-use agents hit sharp capability cliffs as cognitive load rises.

Enable only the servers the current work actually uses. Remove the rest.
Prefer official servers for credentialed tools; never install five speculatively.
Each tool's description eats context on every turn — fewer, sharper tools beat a junk drawer.
Before adding a write-scoped server, add a hook that logs every call. If the agent picks the wrong tool or thrashes, the fix is usually fewer tools with clearer descriptions, not a smarter model.

Track record

Benchmark

22 / 25

test cases passed, vs 13 / 25 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/tool-restraint/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Tool Restraint

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills