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.
git clone --depth 1 https://github.com/0xNyk/lacpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/0xnyk/lacp/hardening-status)<a href="https://agentmods.dev/commands/0xnyk/lacp/hardening-status"><img src="https://agentmods.dev/badge/commands/0xnyk/lacp/hardening-status/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/0xnyk/lacp/hardening-status"><img src="https://agentmods.dev/badge/commands/0xnyk/lacp/hardening-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00025 | $0.00403 |
| Opus 5 | $0.00013 | $0.00201 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
hardening-status 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 10d 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
Show the current LACP hardening status by checking:
- Active hooks: Which LACP hooks are installed and firing
- Context mode: What
LACP_CONTEXT_MODEis set (if any) - Eval checkpoint: Whether continuous QA is enabled and its last result
- Quality gate: Recent telemetry decisions (blocks, allows, scores)
- Handoff: Whether a handoff artifact exists for this directory
Run these commands to gather the data:
# Check hook telemetry (last 5 entries)
tail -5 ~/.local/share/claude-hooks/telemetry.jsonl 2>/dev/null | python3 -c "
import json, sys
for line in sys.stdin:
try:
e = json.loads(line.strip())
print(f\" {e.get('ts','?')[:19]} {e.get('hook','?'):10s} {e.get('decision','?'):6s} {e.get('reason','')[:60]}\")
except: pass
" || echo " No telemetry data"
# Check eval checkpoint
cat ~/.lacp/hooks/contracts/*/eval_checkpoint.json 2>/dev/null | python3 -c "
import json, sys
try:
d = json.load(sys.stdin)
print(f\" Writes: {d.get('write_count',0)}, Last: {d.get('last_result','?')}, Fails: {d.get('fail_count',0)}\")
except: print(' No checkpoint data')
"
# Check context mode
echo " Mode: ${LACP_CONTEXT_MODE:-none}"
echo " Eval checkpoint: ${LACP_EVAL_CHECKPOINT_ENABLED:-disabled}"
Present the results as a clear status report.
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.
- 10d ago First seen · 41 lines · 25 tokens per session scan A 7f97a3cdac87
hardening-status is a command published in the GitHub repository 0xNyk/lacp (304 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 403 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 2026-08-30.
Other commands, from other repositories
prp-plan
Create comprehensive feature implementation plan with codebase analysis and pattern extraction.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
evolution-engine
Scan feedback and generate evolution proposals for rule/skill upgrades.
dev-planner
Generate or update DEV-PLAN.md with phased development plan from Product-Spec.md.