Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ofershap/prompt-compression/auditgit clone --depth 1 https://github.com/ofershap/prompt-compressionWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.00148 |
| Opus 5 | $0.00007 | $0.00074 |
| Sonnet 5 | $0.00003 | $0.00030 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Scan the current project's AGENTS.md, CLAUDE.md, .cursorrules, or similar agent context files for token waste and compression opportunities.
Use the prompt-compression skill for compression techniques and formats.
For each finding:
- Show the bloated section
- Show the compressed version
- Estimate token savings (1 token per ~4 characters)
- Rate impact: high (>50% reduction) / medium (30-50%) / low (<30%)
After scanning, show:
- Total current token estimate
- Total potential savings
- Compressed version of the full file ready to paste
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 23 lines · 14 tokens per session scan A 06079ccf5a97
audit is a command published in the GitHub repository ofershap/prompt-compression (1 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 148 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
email-test-suite
../../services/email/email-test-suite.md.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
spec-intake
Execute the canonical workflow: .agent/workflows/spec-intake.md.
test
Execute the canonical workflow: .agent/workflows/test.md.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.