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/hautc-it/cil/retrievegit clone --depth 1 https://github.com/hautc-it/cilWhat 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 | $0.00025 | $0.00182 |
| Opus 5 | $0.00013 | $0.00091 |
| Sonnet 5 | $0.00005 | $0.00036 |
| Haiku 4.5 | $0.00003 | $0.00018 |
Grade A, and why
retrieve 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 2d ago.
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
/retrieve
Arguments: $ARGUMENTS
Search persistent memory for relevant context.
Step 1 — Search
memory_search("$ARGUMENTS", 8)
Step 2 — Present results
Group by category. For each result:
- Category: [decision|constraint|learning|task|architecture]
- Content: [the stored text]
- Relevance: why this matches the query
Step 3 — If empty
"No memories found for: $ARGUMENTS"
Suggest: use /learn to store relevant context for future sessions.
Step 4 — Apply
Use retrieved context to inform current task. Don't re-derive what's already known.
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.
- 2d ago First seen · 42 lines · 25 tokens per session scan A 91261f8277d5
retrieve is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 182 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
README
Git workflow and quality assurance commands for the claude-skills repository.
convert-to-todowrite-tasklist-prompt
Purpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements.
security-audit
Perform a comprehensive security audit of the codebase to identify potential vulnerabilities, insecure patterns, and security best practice violations.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
hunt
Active vulnerability hunt against a target by invoking tools/hunt.py (which calls vulnscanner.sh against recon/ /). Auto-runs recon first if no recon dir exists. Usage: /hunt target.com.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.