Ready to supercharge your AI agents?

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

Compact Guard · rohitg00 | DecimalAI

agent toolingby rohitg00

Compact Guard

rohitg00/compact-guard

Source rohitg00/pro-workflow ↗License Not recorded

Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/13/2026

What it changes

Passed 22 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill100%

Checks it passed that the model alone missed

The response includes the header 'COMPACT GUARD'.
The response specifies keeping CLAUDE.md under 60 lines.
The response limits the task state summary to a single sentence.

and 10 more in the full report

12 fixed10 passed either way0 still failing0 broke

Pass-rate lift: +55 pp
Tokens: -11%
Agent turns: 0%
Response time: -51%

Model gemini-3.6-flashMeasured 8/13/2026v122 of 22 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/rohitg00-compact-guard/SKILL.md https://app.decimal.ai/s/rohitg00-compact-guard/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rohitg00-compact-guard, 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/rohitg00-compact-guard/ and pins it in .decimal/skills.lock

decimalai skills add rohitg00-compact-guard

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

curl -fsSL --create-dirs -o .claude/skills/rohitg00-compact-guard/SKILL.md https://app.decimal.ai/s/rohitg00-compact-guard/SKILL.md

Raw file: /s/rohitg00-compact-guard/SKILL.md ↗ · machine-readable summary at /s/rohitg00-compact-guard.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

After compacting context, re-reading the active working file, and checking task progress, what is the final step to resume work effectively?

What was checked, without and with the skill
Checked	Without skill	With skill
The response states to resume execution directly from the recorded next steps.	Missed	Passed

case-19 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md69 linessingle file

Compact Guard

Protect important context through compaction cycles. Based on Claude Code internals: compaction restores max 5 files with 5K tokens each, within a 50K total budget.

Trigger

Use before /compact or when auto-compact warning appears.

Key Constants (from Claude Code source)

POST_COMPACT_MAX_FILES_TO_RESTORE = 5 — only 5 files survive
POST_COMPACT_TOKEN_BUDGET = 50K — total restore budget
POST_COMPACT_MAX_TOKENS_PER_FILE = 5K — per-file limit
Auto-compact fires at context_window - 13K buffer

Pre-Compact Checklist

Before compacting, save these to memory or a scratch file:

Current task — What are you working on? One sentence.
Files in progress — Which files are being edited? (max 5 — compaction only restores 5)
Decisions made — Any architectural choices made this session
Blockers — What's preventing progress?
Next steps — What to do immediately after compact

Strategy: Microcompact First

Before full compaction, try microcompact:

Large tool results (test output, grep results) can be trimmed
File reads that are no longer relevant can be dropped
Use subagents for heavy exploration to keep main context clean

Post-Compact Recovery

After compaction, immediately:

Re-read the top-priority file (the one you're actively editing)
Check task list for current progress
Review any scratch notes saved pre-compact
Resume from next steps

Track record

Benchmark

22 / 22

test cases passed, vs 10 / 22 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

rohitg00 / pro-workflow

skills/compact-guard/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

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

avizmarlon/compact-instructionsContext preservation strategy for multi-session projects during context window compaction. Use when running `/compact`, when auto-compact is triggered, or when determining what state to preserve across session boundaries to maintain continuity.Close match+27 pp pass-rate 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

Compact Guard

Trigger

Key Constants (from Claude Code source)

Pre-Compact Checklist

Strategy: Microcompact First

Post-Compact Recovery

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills