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/ayberkyasa/tripod/specnpx skills add ayberkyasa/tripod --skill specgit clone --depth 1 https://github.com/ayberkyasa/tripodWrote 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/ayberkyasa/tripod/spec)<a href="https://agentmods.dev/skills/ayberkyasa/tripod/spec"><img src="https://agentmods.dev/badge/skills/ayberkyasa/tripod/spec.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 | $0.00074 | $0.01041 |
| Opus 5 | $0.00037 | $0.00521 |
| Sonnet 5 | $0.00015 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
spec 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tripod: Spec
You are running phase 1 of the Tripod workflow. The outcome of this skill is exactly two files at the repository root: SPEC.md and CLAUDE.md. They will be two of the only three sources of truth for the entire project (the third, TASKS.md, comes later from /tripod:tasks). Everything you write here will be read by every future coding session, so precision now saves context forever.
Step 1 — Listen
Let the user describe the application in their own words. Do not interrupt with structure. If they invoked this skill without a description, ask for one: "Describe the app you want to build, in as much or as little detail as you like."
Step 2 — Interview in rounds
Ask clarifying questions in rounds of at most 3 questions. Never dump ten questions at once. After each round of answers, either ask the next round or declare the interview done. Two to three rounds is typical; stop as soon as the picture is clear.
Prioritize questions in this order — the earlier categories shape everything downstream:
- Architecture-defining decisions. Backend or fully local? Accounts or anonymous? Online or offline-first? Which platforms and minimum versions?
- MVP boundary. For every feature mentioned, decide: MVP or explicitly deferred? Push back gently on scope — a smaller MVP is almost always right. Propose the cut list; let the user veto.
- Forks in the road. Wherever more than one reasonable approach exists (data source, sync strategy, auth provider, UI paradigm), name the options with one-line trade-offs and ask the user to pick.
- Product feel. Design direction, tone, target user — one question at most; propose a default.
Where a sensible default exists, propose it instead of asking ("I'll assume offline-first with sync later — veto if wrong"). Users should veto, not design from scratch.
Step 3 — Write SPEC.md
Write SPEC.md at the repository root following templates/SPEC.template.md from this plugin (read it before writing). Quality bar:
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.
- 4d ago First seen · 60 lines · 74 tokens per session scan A 00e3b9b5ca62
spec is a skill published in the GitHub repository ayberkyasa/tripod (2 stars, last pushed 19d ago), licensed MIT. It adds 74 tokens to every session and 1,041 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 2026-08-31.
Other skills, from other repositories
artifact-conventions
Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.
plan-authoring
Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
adr-authoring
Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.