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/evb87-tech/corpusWrote 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/evb87-tech/corpus/query)<a href="https://agentmods.dev/commands/evb87-tech/corpus/query"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query/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/evb87-tech/corpus/query"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query.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 | $0.00000 | $0.00609 |
| Opus 5.5 | $0.00000 | $0.00244 |
| Sonnet 5.5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Pre-flight:
CORPUS_VAULT="${CORPUS_VAULT:-$CLAUDE_PLUGIN_OPTION_VAULT_PATH}"
if [ -z "$CORPUS_VAULT" ]; then
echo "No vault configured. Set CORPUS_VAULT (local dev) or configure the vaultPath userConfig option in the installed plugin (exposed as CLAUDE_PLUGIN_OPTION_VAULT_PATH). Neither is set. Run /init-vault <path> to scaffold a fresh vault, then export the path." >&2
exit 1
fi
Verify $CORPUS_VAULT/.corpus-vault exists. If not, refuse and tell the owner to run /init-vault <path>. See corpus-core/rules/08-vault-structure.md.
Answer the owner's question against $CORPUS_VAULT/wiki/: $ARGUMENTS
Detect the posture (research | contradictor | synthesis) from the wording, OR honor an explicit posture token at the start of $ARGUMENTS:
research <question>— retrieve what the wiki already says.contradictor <target>— attack the wiki, surface weaknesses.synthesis <question>— produce a statistical average across sources.
Follow corpus-core/rules/05-query-postures.md:
- Read
wiki/index.mdfirst. - Read identified pages and adjacent ones.
- Answer using only wiki content unless the owner explicitly invites outside knowledge.
- Cite at the end:
Sources: [[page-1]], [[page-2]]. - File-back rules:
- Research producing a reusable lookup → file as wiki page with
type: reference. - Contradictor → file as wiki page with
type: stress-test. Delegate to the contradictor subagent. - Synthesis → write to
output/, never towiki/. Flag the output as a statistical average.
- Research producing a reusable lookup → file as wiki page with
- Append to
wiki/log.md:## [YYYY-MM-DD] query | <question summary> Posture: <research|contradictor|synthesis> Pages consulted: [[a]], [[b]] Filed as: [[result-page]] (research/contradictor only)
Hard rules: never invent sources, never harmonize contradictions, never silently complete with training-data knowledge. See corpus-core/rules/07-anti-lissage.md.
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 · 45 lines · 0 tokens per session scan A 672f9703f885
query is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 609 tokens. 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
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
session-learn
Extract knowledge from the current session. Invoke with /session-learn or "extract this session".
open
Open the memex vault in Finder or Obsidian.
ingest
A command for adding information to a file-based knowledge wiki from web pages, files, or text notes. It classifies the material, updates or creates wiki pages, and adds links between related pages.
evolve
Save knowledge to the cortex vault (Notes or Projects) and update index.