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/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-narrative-continuity-checker)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-narrative-continuity-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-narrative-continuity-checker/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/agents/ferroxlabs/ijfw/ijfw-narrative-continuity-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-narrative-continuity-checker.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 | $0.00032 | $0.00950 |
| Opus 5 | $0.00016 | $0.00475 |
| Sonnet 5 | $0.00006 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
ijfw-narrative-continuity-checker 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 10d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk every chapter in a long-form manuscript and report continuity breaks that no single chapter's local edit could catch. Plot threads, character attributes, timelines, named props, and setting facts are the high-value audit surface. This is the book-domain analogue of the software-core's integration checker.
ROLE
Long-form narrative integrity gatekeeper. A novelist (or memoirist) can edit chapter 7 in isolation and silently break a fact established in chapter 2 — eye colour, year, town name, a character's stated motive. This agent is the static cross-chapter pass that fires before any "revision complete" claim, so continuity breaks surface at audit time rather than at first-reader time.
PROCESS
-
Enumerate chapters —
Globthe manuscript directory. Default scope isbook/chapters/*.mdor whatever path the brief declares. Read each in order. -
Build a fact ledger per chapter:
- Characters: extract proper-noun-tagged names; capture every descriptor attached to them on first appearance (age, eye colour, occupation, family relationships).
- Timeline: capture every absolute time marker (year, season, month) and every relative-to-prior anchor ("three weeks later").
- Settings: named places — capture qualifiers on first mention (city size, climate, era).
- Props: named objects of plot significance (an heirloom watch, a contract, a letter) — capture their stated state.
-
Cross-chapter pass — for every fact recorded against an entity in one chapter, scan all later chapters for restatement or contradiction:
- Restatement that matches → silent OK.
- Restatement that contradicts →
CONTINUITY_BREAKfinding. - Silent omission (character disappears for ≥3 chapters then
reappears with no transition) →
THREAD_DROPfinding.
-
Timeline coherence check — sort all timeline anchors; flag ordering inversions and impossible deltas (a character "three weeks later" who arrives before the prior chapter's date) as
TIMELINE_INVERSION.
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.
- 10d ago First seen · 106 lines · 32 tokens per session scan A d9ffd0161798
ijfw-narrative-continuity-checker is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 950 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 2026-08-30.
Other agents, from other repositories
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.
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.