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 commands/agentic-swe/agentic-swe/swe-tuigit clone --depth 1 https://github.com/agentic-swe/agentic-sweWhat 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 | $0.00000 | $0.00436 |
| Opus 5 | $0.00000 | $0.00218 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
swe-tui 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 2d 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.
What it actually says
/swe-tui
Launch a terminal-based live cockpit for monitoring pipeline execution.
Usage
/swe-tui [--work-dir <path>] [--cwd <repo-path>]
Behavior
- Discover the active work item from
.worklogs/(newest non-completed, or specified via--work-dir). - Start a terminal UI displaying:
- State bar: current state, track, budget remaining, cost used
- History panel: scrollable list of transitions with timestamps
- Gate panel: active gate prompts (ambiguity-wait, approval-wait) with resolution controls
- Event stream: real-time events from the pipeline (state changes, subagent spawns, doubt findings)
- Budget burn: visual cost/token chart
- Events are consumed via the dashboard event stream (WebSocket from
swe-dashboardor file-watch onstate.json). - Gate resolution: when a gate event appears, the TUI prompts the human for input and writes the resolution to the appropriate artifact.
Constraints
- Read-only by default — gate resolution requires explicit
--interactiveflag. - Falls back to polling
state.jsonevery 2 seconds if WebSocket is unavailable. - Designed for SSH/headless environments where the browser dashboard is not accessible.
Implementation Notes
Uses Node built-in readline for minimal dependency. Implementation: ${CLAUDE_PLUGIN_ROOT}/scripts/swe-tui-server.cjs.
Exported API for tests and programmatic use:
formatBudgetBar(remaining, total, width)→ stringdiscoverWorkDir(cwd)→ string|nulldiscoverAllWorkDirs(cwd)→ string[]renderWorkItem(state, opts)→ stringchooseLayout(itemCount, termWidth)→ 'side-by-side'|'stacked'
ASCII mascot is rendered only when process.stdout.isTTY === true and NO_COLOR is not set. CI/pipe environments get plain-text output automatically.
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.
- 2d ago First seen · 41 lines · 0 tokens per session scan A 0f0288093544
swe-tui is a command published in the GitHub repository agentic-swe/agentic-swe (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.