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/leji-org/leji/coregit clone --depth 1 https://github.com/leji-org/lejiWhat 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 | $0.00002 | $0.00233 |
| Opus 5 | $0.00001 | $0.00117 |
| Sonnet 5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
Agent Core 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.
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.
- 2d ago First seen · 28 lines · 2 tokens per session scan A b4388b89c1c0
Agent Core is an agent published in the GitHub repository leji-org/leji (5 stars, last pushed 5d ago), with no licence file. It adds 2 tokens to every session and 233 once invoked, about $0.0000 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
shep-cli-command-creator
Scaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Use when a use case already exists and the…
shep-port-extractor
Fixes the 'application layer imports from infrastructure' violation. Given ONE concrete infrastructure symbol (class, function, or constant) and the list of application-layer files that import it, creates a port interface in application/ports/output/, moves (or keeps) the concrete behind it in infrastructure/, rewires…
shep-use-case-creator
Scaffolds a new application-layer use case with TDD (RED test file first, then minimal GREEN implementation), wires it into the DI container, and verifies. Follows shep's mandatory patterns exactly (tsyringe decorators, port injection by string token, no infrastructure imports, no console.). Use when you need a new…
shep-web-route-creator
Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…
supervisor-agent
The Supervisor Agent is responsible for evaluating agent collaboration events and deciding whether Shep should approve, reject, escalate, or advise on the next step.
shep-clean-arch-auditor
Read-only clean architecture auditor for shep. Scans a specified directory for dependency-rule violations, magic literals, singletons, oversized files, and duplication. Appends findings to a violations log in the canonical format. Use when doing a fresh sweep of a layer or a sub-tree — NOT for fixing, only for…