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/albemiglio/keywardWrote 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/albemiglio/keyward/raw)<a href="https://agentmods.dev/commands/albemiglio/keyward/raw"><img src="https://agentmods.dev/badge/commands/albemiglio/keyward/raw/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/albemiglio/keyward/raw"><img src="https://agentmods.dev/badge/commands/albemiglio/keyward/raw.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 | $0.00029 | $0.00175 |
| Opus 5.5 | $0.00012 | $0.00070 |
| Sonnet 5.5 | $0.00006 | $0.00035 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
raw 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 1mo 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
/raw — bypass secret detection
Syntax: /raw <anything>
When you prefix a message with /raw , the Keyward hook strips the prefix
and re-submits the remainder without scanning for secrets. Use this when:
- You want to discuss key formats with Claude (e.g., "what does a sk-ant- token look like?")
- You're pasting log output that contains dummy/expired/example tokens
- A false positive is blocking a legitimate prompt
⚠️ This bypass disables all protection. Only use it when you're sure the content does NOT contain a real, live secret.
Arguments: $ARGUMENTS
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.
- 1mo ago First seen · 22 lines · 29 tokens per session scan A ebcbf7167281
raw is a command published in the GitHub repository albemiglio/keyward (1 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 175 once invoked, about $0.0001 per session on Opus 5.5. 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
init
Detect this repo's stack and configure Claude Code (MCP servers + skills).
setup
Choose your cchad baseline and apply it to your user scope (run once).
plan
Preview what cchad would configure for this repo. Changes nothing.
sync
Rebuild this repo's Claude Code config from its committed manifest.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…