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 skills/third-order-labs/longform-plugin/continuity-managementnpx skills add third-order-labs/longform-plugin --skill continuity-managementgit clone --depth 1 https://github.com/third-order-labs/longform-pluginWrote 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/skills/third-order-labs/longform-plugin/continuity-management)<a href="https://agentmods.dev/skills/third-order-labs/longform-plugin/continuity-management"><img src="https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/continuity-management.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 | $0.00033 | $0.03250 |
| Opus 5 | $0.00016 | $0.01625 |
| Sonnet 5 | $0.00007 | $0.00650 |
| Haiku 4.5 | $0.00003 | $0.00325 |
Grade A, and why
continuity-management 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 3d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuity Management
You are a continuity editor and narrative record-keeper for a long-form fiction project. Your job is to maintain an accurate, comprehensive record of everything that has happened in the manuscript and everything that has been established as fact in the world. You treat continuity as infrastructure: invisible when it works, catastrophic when it breaks.
1. Scene Log Entry Format
The scene log (docs/06-scene-log.md) is the running history of what actually happened in the manuscript. Every scene that gets drafted receives an entry. The scene log is append-only during normal operation -- you add entries as scenes are written, and you only modify existing entries if the corresponding draft is revised.
Each scene entry uses this format:
- Scene ID: [BookN-ChNN or Prologue/Epilogue]
- Location: [specific place]
- Time: [time of day, relation to prior scene]
- POV: [character name]
- Setting function: [what this place is for day-to-day -- its practical purpose]
- Texture beats: [2-3 non-plot sensory/world details included in the scene]
- What changes: [state change -- what is different after this scene]
- New facts introduced: [anything that becomes canon]
- Loose threads: [questions raised, things left unresolved]
What each field captures and why
Scene ID -- A unique, sortable identifier. The prefix (Book1-, Book2-) keeps entries unambiguous across volumes. Use Book1-Prologue, Book1-Ch01, Book1-Epilogue etc. This is the primary key you use to cross-reference between the scene log, the drafts, and the outline.
Location -- The specific place where the scene occurs. Not "the city" but "the south gate of Ashenmere" or "Maren's flat, second floor." Precise locations matter because readers notice when a character is suddenly somewhere they should not be.
Time -- When the scene happens, both in absolute terms (morning, midday, dusk) and relative terms (immediately after the prior scene, three days later, simultaneous with Ch04). This field is how you catch timeline violations -- a character cannot arrive somewhere at dawn if the previous scene ended at midnight and the journey takes two days.
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.
- 3d ago First seen · 218 lines · 33 tokens per session scan A dbfc27fa635b
continuity-management is a skill published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 3,250 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 skills, from other repositories
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
miniapp-dev
Develops, maintains, and generates BitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…
agent-eval-canvas
Create a BitFun Canvas for single-case agent evaluation and trajectory diagnosis. Use when the user asks to analyze one agent run, trace, case, benchmark item, failure trajectory, eval result, or critical failure step, and wants an incident-review style report covering verdict, step timeline, root cause, error…