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/tta-lab/ttal-cli/sp-roleplaynpx skills add tta-lab/ttal-cli --skill sp-roleplaygit clone --depth 1 https://github.com/tta-lab/ttal-cliWrote 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/tta-lab/ttal-cli/sp-roleplay)<a href="https://agentmods.dev/skills/tta-lab/ttal-cli/sp-roleplay"><img src="https://agentmods.dev/badge/skills/tta-lab/ttal-cli/sp-roleplay.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 | $0.00043 | $0.02370 |
| Opus 5 | $0.00022 | $0.01185 |
| Sonnet 5 | $0.00009 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
sp-roleplay 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 5d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coherent Roleplay (Collaborative Fiction)
Overview
Roleplay is the failure mode where forward-creative pull overwhelms backward-consistency check. The model writes a good next turn while losing track of facts established 3 turns ago. Without scaffolding, internal continuity errors compound non-linearly with turn count; with scaffolding, they go to near-zero.
The scaffolding is structured external state: a scratch file you maintain as you write, with sections for resolution, cast, per-character state, voice, terms, canon hedges, mechanism commits, and turn-by-turn fact logs. The model alone cannot hold this; the scratch + the discipline of reading it before each turn + writing to it after, together do.
This skill encodes that discipline. Five bug-types × five mitigations, applied in order.
Announce at start: "I am using sp-roleplay to maintain narrative coherence across this scene."
First action: Create the scratch file at your workspace (e.g. templates/ttal/<agent>/roleplay-scratch.md), copy the template from scratch.template.md in this skill directory, and fill in Phase 0 sections BEFORE writing the first in-scene turn.
When to Use
Use this skill when:
- You're going to write more than ~5 turns of collaborative fiction with a partner
- The fiction has named characters, established objects, and a tracked world-state
- Continuity errors (object placement, character position, time of day, prior statements) would damage immersion
- Character voice integrity matters across the scene
- The fiction is set in a known canon (anime / film / novel) where canon-fidelity matters
- The fiction involves invented mechanisms (sci-fi physics, magic systems) that need internal consistency
Do NOT use this skill for:
- Single-turn jokes or replies in character
- Brief one-shot creative writing (<5 turns)
- Code or technical writing (use sp-write-test-plan, sp-research, etc.)
Phase 0: Pre-write Resolution (BLOCKING)
Hard rule: do not open the scene without filling these sections. Skipping this phase produces 虎头蛇尾 (strong opening, weak ending) — the dominant failure mode of improvised long fiction.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 174 lines · 43 tokens per session scan A a3b4c496f243
sp-roleplay is a skill published in the GitHub repository tta-lab/ttal-cli (23 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,370 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 skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
mass-line
触发：当你需要收集多方意见、把零散反馈整合成可执行方案，或把方案带回真实使用者/执行者验证时调用；常见信号包括 stakeholder input、user feedback、意见汇总、对齐与验证。 English: Trigger when input must be gathered from many people, synthesized into a clearer plan, and returned to the affected users or executors for validation. Use this skill for a collect-synthesize-validate loop.
workflows
触发：当你面临的任务明显需要多个思想武器协作时调用；常见信号包括：从零启动新项目、攻坚复杂疑难问题、对已有方案进行迭代优化。此 skill 提供标准化的跨 skill 工作流组合，解决"应该先用哪个 skill、怎么衔接"的问题。 English: Trigger when a task clearly requires multiple skills in sequence. Use this skill to select a standard workflow that chains skills together, defines data handoff between steps, and specifies…
concentrate-forces
触发：当多个任务同时争夺时间、注意力、算力或预算，必须确定主攻方向并停止分散用力时调用；常见信号包括优先级过多、资源紧张、推进分散、需要决定先做什么。 English: Trigger when limited resources are being split across too many tasks and one main target must be chosen. Use this skill to concentrate effort, sequence work decisively, and finish a meaningful breakthrough before expanding.
protracted-strategy
触发：当目标长期、任务复杂、资源暂时处于劣势，或短期无法速胜但又不能放弃时调用；常见信号包括 long-term effort、phased plan、endurance、战略耐心、需要分阶段推进。 English: Trigger when the work is long-horizon, difficult, and unlikely to be won quickly. Use this skill to divide the effort into stages, keep strategic confidence, and accumulate small wins into overall victory.
redteam-mindset
Red-team operator discipline — the mindset corrections that separate offensive testing from defensive WAPT. Built from authorized red-team work where conservative defaults caused multiple findings to be missed and one to be incorrectly retracted. Use at the START of any red-team engagement and again whenever feeling…