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 agents/hiphapis/loopcraft/verifiergit clone --depth 1 https://github.com/hiphapis/loopcraftWhat 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 | $0.00049 | $0.00375 |
| Opus 5 | $0.00024 | $0.00187 |
| Sonnet 5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
verifier 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 34 lines · 49 tokens per session scan A 9311a1e25bc9
verifier is an agent published in the GitHub repository hiphapis/loopcraft (3 stars, last pushed 1mo ago), with no licence file. It adds 49 tokens to every session and 375 once invoked, about $0.0002 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 agents, from other repositories
layer-leak-auditor
Read-only auditor that checks a note, file, or diff for cross-scope leaks before publishing, sharing, or committing. Only applicable when the OPTIONAL wall is enabled — i.e. some scope in AIOS/Systems/layers.tsv declares identifying tokens. Use before any external-facing action (publish, post, send, apply) or when…
publish-verify
Read-only post-publish verifier. Given a published URL (or repo path), fetches the live artifact, runs the cross-scope token grep against it, and traces every first-person factual claim back to the vault's confirmed-history notes — unsourced claims are fabrication-risk. Run after ANY external publish (blog post…
graphify-scout
Cheap codebase-investigation scout — queries the graphify knowledge graph (graphify-out/) first, then verifies every hit with grep before reporting. Use for "where does X live / how does Y flow / what touches Z" questions before reading files or spawning heavier agents.
ingest-worker
Processes ONE queued session digest from +/sessions/ / .md into its /projects/ note, in an isolated context. Spawn one per digest when fanning out /aios-ingest; the orchestrator handles Knowledge Map, Log, the leak gate, archiving, and the commit. Prefer the fast model tier — this is mechanical synthesis.
wiki-lint-runner
Read-only health-check of the knowledge wiki (schema, staleness, coverage gaps, Knowledge Map drift, orphans, duplicates, contradictions). Runs the AIOS/Skills/wiki-lint.md audit in an isolated context so its file-reading noise doesn't pollute the main conversation. Use when asked to "lint the wiki", "wiki lint", or…
wiki-query
Read-only wiki researcher — answers a question from the knowledge wiki for ONE identity layer (as defined in AIOS/Systems/layers.tsv) by reading the Knowledge Map, traversing wikilinks, and returning a cited answer. Use for "what does the wiki say about X" questions so the read-heavy traversal doesn't pollute the main…