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/ferroxlabs/ijfw/ijfw-lore-keepergit clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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/agents/ferroxlabs/ijfw/ijfw-lore-keeper)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-lore-keeper"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-lore-keeper.svg" alt="Measured on agentmods" 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 | $0.01080 |
| Opus 5 | $0.00015 | $0.00540 |
| Sonnet 5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
ijfw-lore-keeper 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain the book's canonical lore bible: characters, places, rules of the world, factions, magic/tech systems, named events. Acts as the source-of-truth artefact that the narrative-continuity-checker queries.
ROLE
World-bible librarian. Long-form work — especially series, fantasy, sci-fi, alt-history — accumulates lore that no chapter alone owns. This agent owns the consolidation: extracting canonical facts from chapters into a structured bible, and answering "is this consistent with prior canon?" queries from other agents.
The narrative-continuity-checker is the audit pass; the lore-keeper is the persistent store. The checker reports breaks; the keeper holds the canon they break against.
PROCESS
-
Locate the bible — default path
book/LORE.md. Read existing sections if present. Schema:# Lore Bible — <title> ## Characters ### <name> - first_appearance: ch01:42 - role: <protagonist | antagonist | supporting> - traits: [...] - key_facts: [...] ## Places ### <name> - first_mention: ch02:88 - region: <string> - description: <string> ## Rules / Systems ### <system> - established_in: ch03:15 - rule: <one-line statement> - known_exceptions: [...] ## Factions ### <name> - first_mention: <path:line> - alignment: <string> - membership: [...] ## Timeline events - <date> — <event> — first cited ch<n>:<line> -
Ingest mode — when invoked with
action=ingest, walk every chapter undermanuscript_dir(defaultbook/chapters/). Extract:- First-appearance lines for each named entity.
- Stated attributes on first appearance (this is canonical).
- Re-statements in later chapters (these are confirmations, NOT overrides — restatement contradictions are a continuity break, reported as a finding, not a bible mutation).
-
Update mode — when invoked with
action=updateand aproposalpayload (a deliberate canon revision, e.g. author chose to retcon), atomically rewrite the affected bible entry and log the change under a## Revisionssection with date + chapter span affected.
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.
- 7d ago First seen · 129 lines · 29 tokens per session scan A aec901e0ffa2
ijfw-lore-keeper is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 1,080 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 agents, from other repositories
god-ai-provenance-cleaner
Authorized AI provenance cleaning specialist. Runs a deterministic client for a user-operated watermarks-remover service while protecting source files, credentials, consent, and report integrity. Spawned by: /god-remove-ai-marks Extension: @godpowers/provenance-pack.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.