Ready to supercharge your AI agents?

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

Get Started Free →

Context Budget · archive228 | DecimalAI

agent toolingby archive228

Context Budget

archive228/context-budget

Source archive228/loopkit ↗License MIT

Keep the agent's context lean so accuracy doesn't collapse.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 23 of 23 test cases with the skill, and 20 of 23 without it.

Without skill87%

With skill100%

Checks it passed that the model alone missed

Advise retaining only the selected decision or benchmark conclusion
Recommend reviewing and trimming standing context on a regular weekly cadence
Identify context rot or accuracy degradation as the reason to avoid full file dumps

and 1 more in the full report

3 fixed20 passed either way0 still failing0 broke

Pass-rate lift: +13 pp
Tokens: -36%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 8/16/2026v123 of 23 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-context-budget/SKILL.md https://app.decimal.ai/s/archive228-context-budget/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-context-budget, 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-context-budget/ and pins it in .decimal/skills.lock

decimalai skills add archive228-context-budget

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 ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

A team manages a repository with a `CLAUDE.md` context file. Over time, team members added detailed examples of 12 past bug fixes and entire file schemas. How often should standing project context files be reviewed and pruned?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommend reviewing and trimming standing context on a regular weekly cadence	Missed	Passed

case-10 · 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

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.

Track record

Benchmark

23 / 23

test cases passed, vs 20 / 23 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/context-budget/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Context Budget

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills