TAP Runtime — Development skill for Claude Code
Run your coding agent's repeated work as small sandboxed programs that borrow its tools and ask before changing anything.
How to install TAP Runtime
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Telara-Labs/TAP-Runtime and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What TAP Runtime does
Run your coding agent's repeated work as small sandboxed programs that borrow its tools and ask before changing anything. Includes tap discover, which finds those procedures in your own agent history, locally.
Alternatives in Development
- Build Program — Build Solana programs (Anchor, Pinocchio, native), incl 105 ★
- Assess Project — DEPRECATED: Use /bootstrap-project instead 60 ★
- Crucible Write — Draft novel prose scene-by-scene from Crucible outlines 58 ★
README
TAP Runtime
TAP (Trusted Agent Primitives) lets agents build their own internal tools as reusable blocks of code. We expect agents to write most of these primitives as they work. Humans can write them too.
People ask agents to get work done across source control, ticketing, CRM, and other company systems. A different project or account often needs the same procedure. Much like engineers build software for people, agents can put those repeatable steps in code, give them a defined interface, and call them again with new inputs. The code handles the procedure and returns a result or failure; the agent decides what to do next.
Read [Why TAP](WHY-TAP.md) for the thinking behind the project.
Quick start
npm install -g @telaralabs/tap # the tap CLI
tap setup # connect it to the agents installed here
tap discover # what you keep asking your agents to do
No account, registry or server is needed. MIT licensed.
`tap discover` looks for reusable procedures in local agent histories and proposes primitives for review. To write one yourself, start with the [authoring guide](docs/writing-a-primitive.md) and [examples](examples/). A package contains `primitive.yaml` and an entrypoint (`main.sh`, `main.py`, `main.js` or `main.ts`). The runner executes it in a WebAssembly sandbox, using the host's tool connections and approval paths. Connected-tool execution is supported in Claude Code and Codex; see [Where it runs](#where-it-runs) for the other clients.
An example: checking a release
An agent could write a primitive that takes a repository, a candidate commit, and a set of release requirements, then:
- Finds the changes since the previous release.
- Retrieves the CI results for the candidate commit.
- Follows references to the work items and reviews associated with those changes.
- Handles pagination, matches records by their IDs, and checks the requirements.
- Returns the checks that passed, anything m
Related Skills
Simplified Technical English For Agent Output ASD St100
Claude skill for writing manuals, procedures, and safety text in ASD-STE100 Simplified Technical English (Issu
ShrinkCode
A Claude Skill that compresses bloated codebases into fewer lines without changing behavior: finds duplicate b
CLI Anything Capcut
CapCut/JianYing draft scripting CLI built on pyCapCut. Includes Claude Code skill.
Recall Session
Answer a question from past session evidence without changing anything
Reflect Session
Understand what this session taught us without changing anything
Mini Agent Framework
A small, reusable, single-agent framework built from scratch in Python. It uses a bounded ReAct execution loop
Related Agents
Doey Scaffy Pattern Discoverer
Runs scaffy discover and analyzes git history for repeated structural, injection, and refactoring patterns wor
Search Conversations
Use when searching Claude Code and Codex history for information learned in past conversations or prior experi
History Analyst
Analyzes git history for changed files to surface context: recent refactors, reverted changes, repeated bug fi