Ready to supercharge your AI agents?

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

Get Started Free →

Context Budget — measured AI agent skill | DecimalAI

archive228/context-budget

NewSkillScoreMaintained

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

agent-toolingby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-context-budget/SKILL.md

decimalai skills pull archive228-context-budget --out .claude/skills/

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

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

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

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7h ago

Yes — +13% lift-36% tokens0% turns100% of whole cases pass with skill (23/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-44%	0%
case-10	✗→✓	▲ Improved	-63%	0%
case-17	✗→✓	▲ Improved	-41%	0%
case-02	✓→✓	＝ Same ✓	-42%	0%
case-03	✓→✓	＝ Same ✓	-43%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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/context-budget/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Context Budget

More context is not better. Past a threshold, accuracy falls off a cliff (context rot).

Don't dump whole files — read the relevant function/section, not the 2000-line module.
Summarize, don't accumulate — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
Drop dead context — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
State on disk, not in context — progress goes to a file the next turn re-reads, not into an ever-growing prompt.

A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.

Want to see if archive228/context-budget would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.