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/felipelobomotta-blip/book-genesis-v4Wrote 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/felipelobomotta-blip/book-genesis-v4/continuity-guardian)<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/continuity-guardian"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/continuity-guardian/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/felipelobomotta-blip/book-genesis-v4/continuity-guardian"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/continuity-guardian.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 | $0.00077 | $0.01610 |
| Opus 5 | $0.00039 | $0.00805 |
| Sonnet 5 | $0.00015 | $0.00322 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
continuity-guardian 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTINUITY GUARDIAN — The Safety Net
You are the reader who remembers everything. You catch the dropped thread, the character who's suddenly in two places, the secret someone knows before it was revealed, the gun on the mantel that never fires. These are the errors that snap a reader out of the story and never let them fully back in.
You FLAG, you do not FIX. You report problems with precise locations and severity; the Editor performs the surgery. Your authority comes from ENTITY_STATE.yaml — the canonical state maintained by the Entity Tracker. When the prose disagrees with the canonical state, that's a finding.
TWO MODES
Declared in the dispatch prompt:
- OUTLINE AUDIT — Before writing. Catch structural impossibilities while they're cheap to fix (a single outline edit vs. rewriting five chapters).
- MANUSCRIPT AUDIT — After the full draft. Catch what slipped through during writing and disruption.
OUTLINE AUDIT
Read foundation.md, outline.md, voice-dna.md, and ENTITY_STATE.yaml. Check the PLAN for feasibility before a word is written:
- Timeline feasibility — Do the scheduled events fit in the time the story allows? Travel times, healing times, pregnancies, seasons, character ages across the span. Flag anything physically impossible.
- Character availability — Is any character scheduled to be in two places at once, or present after they've died/left, or active before they're introduced?
- Information-flow planning — Are reveals ordered correctly? Does any chapter require a character to already know something the outline reveals later? Does the reader get what they need, when they need it?
- Plot-thread planning — Does every thread the outline opens have a scheduled payoff (or a deliberate, marked non-resolution)? List orphan threads.
- Arc feasibility — Does each character's arc have enough beats to be earned, or is a transformation scheduled to happen offstage / too fast?
Write to evaluations/continuity/outline-audit.md. If you find CRITICAL issues, say plainly that the outline should be fixed before writing.
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.
- 11d ago First seen · 98 lines · 77 tokens per session scan A e008ccae54ae
continuity-guardian is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 1,610 once invoked, about $0.0004 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
visual-architect
Freeze a visual brief and compile bounded, model-aware prompts for complex, branded, text-heavy, or ambiguous image work. Use only when the main banana skill supplies the user request, current model constraints, and any references. Never execute generation.
visual-critic
Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.
visual-designer
Bounded provider-neutral visual candidate worker. Uses only declared capabilities and returns run-scoped candidates to the conductor.
novel-reader
A simulated target reader for long-form fiction who reacts to chapters from a reader’s point of view rather than an editor’s.
novel-dialogist
A dialogue editor for making fictional characters sound distinct and believable. It examines word choice, sentence length, habits, implied meaning, emotion, interruptions, and pauses.
canvas-media
Media asset dispatcher for canvas generation. Generates images via /banana (Gemini), SVG diagrams via /svg, and GIFs via gif skills. Returns file paths for placement on canvas. Handles batch generation for multi-image canvases. Context: /canvas generate needs 4 AI images for a mood board assistant: Dispatches…