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-researchnpx skills add tta-lab/ttal-cli --skill sp-researchgit 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-research)<a href="https://agentmods.dev/skills/tta-lab/ttal-cli/sp-research"><img src="https://agentmods.dev/badge/skills/tta-lab/ttal-cli/sp-research.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 | $0.00029 | $0.01747 |
| Opus 5 | $0.00015 | $0.00873 |
| Sonnet 5 | $0.00006 | $0.00349 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
sp-research 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Overview
Conduct structured, multi-source research that produces actionable findings. Research is synthesis with a stance, not aggregation. Every finding should connect to a "so what?" that helps the team make a decision.
Announce at start: "I'm using the research skill to investigate this."
Before You Start: Value Stance
Before touching any source, write down one sentence answering:
"My purpose is to calibrate our design intuition — or to copy features from prior art?"
If you can't answer, ask. Purpose-wrong research becomes anxiety-driven link-gathering — it fills the flicknote and drains trust.
Corollaries:
- Don't over-research when we're ahead. If the team already has a working primitive or novel approach, external comparisons have diminishing signal. Research cost must match decision value.
- Check existing primitives first. Before cataloging how others solve X, verify we haven't already solved X in our own system. Reinvention-via-research is the quiet failure mode.
- Extract design philosophy, not implementation. When studying a competitor or OSS project, the prize is the design stance / mental model, not the code. Write down "what they believe" before "what they built."
Epistemic Hygiene — Know What You Know
Research analysis is only as good as the foundations under it. Apply these rules in output, not just internally:
Tag every factual claim:
- 🔍 Verified — from a search or document you just read (cite it)
- 💭 Interpretation — reasoning built on verified facts (show the chain)
- 🤔 Speculation — pattern-guessing (flag it; move to branching scenarios when you can: "if X → A, if Y → B")
- ❓ Unknown — say so; don't fill the gap
Core operating rules:
- Verify before analyze. Memory is for directions, not details.
- Check new claims before building on them. If a new fact enters the conversation, treat it as a claim until verified.
- On correction, re-examine the whole chain. A corrected fact may invalidate every conclusion downstream — don't patch locally.
- If tools can't find it, say so and ask. No "one more sentence" temptation — if the foundation is unknown, the analysis is deferred, not rebranded as speculation.
- Honest dead ends beat forced conclusions. Partial findings with clear gaps are more valuable than a smooth answer built on air.
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 · 157 lines · 29 tokens per session scan A ecc4ae6d2fe5
sp-research is a skill published in the GitHub repository tta-lab/ttal-cli (23 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,747 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 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…