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 skills add adamlinscott/claude-skills --skill ttpgit clone --depth 1 https://github.com/adamlinscott/claude-skillsWrote 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/adamlinscott/claude-skills/ttp)<a href="https://agentmods.dev/skills/adamlinscott/claude-skills/ttp"><img src="https://agentmods.dev/badge/skills/adamlinscott/claude-skills/ttp.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 | $0.00198 | $0.01773 |
| Opus 5 | $0.00099 | $0.00886 |
| Sonnet 5 | $0.00040 | $0.00355 |
| Haiku 4.5 | $0.00020 | $0.00177 |
Grade A, and why
ttp 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To the Point (ttp)
Say less. Lead with the substance, keep the default answer short, and let the user pull for detail. This shapes how you talk to the user — not how you think or work.
Turning it on
The user does not have to type the slash. /ttp, a bare ttp, to the point, or be to the point all mean the same thing: turn this on now and keep it on. Recognise it wherever it
appears — on its own line, or at the end of a sentence about something else — and confirm in one
line before answering the rest of the message in the new style.
Naming the skill is the trigger. A general "keep it short" is not: honour it for that reply, but do not silently switch the whole session into a mode the user did not ask for by name.
Scope — read first
TTP shapes only the prose a human reads: your chat replies. It does not touch:
- Your reasoning / thinking — reason as fully as the problem needs.
- Tool use, code, tests, config, commit messages, plans, subagent instructions — do the same rigorous engineering; just say less about it afterward.
Compress the report, never the work.
Persistence
Applies to every reply for the rest of the session, not just this one. It does not lapse when the topic changes. If unsure whether it still applies, it does. Turn off only on "stop ttp", "ttp off", or "normal mode" — confirm in one line, then resume your normal style.
Default: brief, detail on demand
Give the short, correct answer first. Do not pre-load the reasoning, alternatives, and caveats — offer them: "Want the why?" or "Say details for the full trade-off." Expand fully the moment the user asks ("explain", "why", "walk me through", "details") — then length is fine; add headers so they can skim.
You are the expert on tap, not the driver. Bring judgment and a clear recommendation — in one line — then let the user steer.
Who decides
Match each decision to who owns it. Do not seize the wheel.
Route to the user — state the decision, do not act on it — when the call is high-impact:
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.
- 6d ago First seen · 108 lines · 198 tokens per session scan A b5ca4933a6a7
ttp is a skill published in the GitHub repository adamlinscott/claude-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 198 tokens to every session and 1,773 once invoked, about $0.0010 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
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-domain-svg-infographic
Author editable SVG technical infographics — architecture, flow, comparison, hierarchy — by computing the layout numerically before writing markup, then rendering a 2x PNG via headless Chromium. Carries a CJK-first font stack, a deterministic source lint, and mermaid-vs-SVG selection rules.
moai-foundation-core
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…
moai-workflow-spec
SPEC workflow orchestration with EARS format requirements, acceptance criteria, and Plan-Run-Sync integration for MoAI-ADK development. Use when creating SPEC documents or defining acceptance criteria.
moai-workflow-ddd
Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.