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/nextnpx skills add ayberkyasa/tripod --skill nextgit 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/next)<a href="https://agentmods.dev/skills/ayberkyasa/tripod/next"><img src="https://agentmods.dev/badge/skills/ayberkyasa/tripod/next.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 | $0.00744 |
| Opus 5 | $0.00037 | $0.00372 |
| Sonnet 5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
next 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tripod: Next
You are running the execution loop of the Tripod workflow. One invocation = one task, taken from TASKS.md, implemented completely, verified, checked off, committed.
The loop
- Orient. Read
TASKS.mdand find the first unchecked task (top to bottom). If the user named a specific task, use that one instead — but warn if it has unfinished sequential predecessors. ConsultSPEC.mdfor the requirements the task references andCLAUDE.mdfor every rule that governs the implementation. These three files are the only project documentation; do not invent others. - Announce. State the task number, title, and your implementation plan in a few sentences. If the task turns out to be ambiguous or its "Done when" cannot be verified as written, say so and propose a sharper wording before coding.
- Implement. Follow CLAUDE.md exactly: folder structure, architecture, naming, style, testing rules, teaching mode if present. Stay inside the task's scope — if you notice missing work that belongs to another task, note it, don't do it. If you discover work that belongs to no task, propose adding a task to TASKS.md rather than silently expanding this one.
- Verify. Run the task's "Done when" condition literally (build, tests, lint — whatever it names). Do not check the box on a red or unverified condition, ever. If verification requires something you cannot do (a physical device, a real outdoor walk), implement everything, state precisely what remains for the user to verify, and leave the box unchecked with a
(pending manual verification: …)note. - Record. Change the task's
[ ]to[x]in TASKS.md. If implementation revealed durable knowledge (a changed constant, a discovered constraint), update SPEC.md or CLAUDE.md — with the user's confirmation — so the three files stay truthful. - Commit. One commit per task, message per the convention in CLAUDE.md (default: conventional commits), e.g.
feat: 1.3 Douglas-Peucker simplification. Never commit a broken build. - Report. Summarize what was built, show the verification result, and name the next task on deck. If CLAUDE.md has a teaching mode, end with its "what to notice" summary.
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 · 30 lines · 74 tokens per session scan A 382a4f377554
next is a skill published in the GitHub repository ayberkyasa/tripod (2 stars, last pushed 20d ago), licensed MIT. It adds 74 tokens to every session and 744 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.