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 agents/modem-dev/hunk/live-session-controlgit clone --depth 1 https://github.com/modem-dev/hunkWhat 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 | $0.00017 | $0.00417 |
| Opus 5 | $0.00009 | $0.00209 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
live-session-control 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 yesterday.
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
Each normal Hunk TUI registers with one loopback daemon. hunk session ... finds a registered window and sends it review actions.
Find the session
hunk session list
hunk session get --repo .
hunk session context --repo .
Use --repo <path> for normal worktrees. Use an explicit session ID when multiple windows share a repository.
Inspect without overloading context
hunk session review --repo . --json
This returns files and hunks. Add flags only when required:
hunk session review --repo . --include-notes --json
hunk session review --repo . --include-patch --json
Navigate the visible window
hunk session navigate --repo . --file src/App.tsx --hunk 2
hunk session navigate --repo . --file src/App.tsx --new-line 372
hunk session navigate --repo . --next-comment
Hunk numbers are 1-based. Absolute navigation needs a file and exactly one hunk, old-line, or new-line target.
Reload the review
Always place -- before the nested Hunk command:
hunk session reload --repo . -- diff
hunk session reload --repo . -- show HEAD~1 -- README.md
Advanced reloads can target the live window by --session-path and load from a separate --source directory. Prefer --repo until those roles genuinely need to differ.
Diagnose local access
If a visible Hunk window does not appear in session list, an agent sandbox may block loopback access. Hunk's daemon is intentionally local-only; retry with the agent's network/sandbox permission rather than exposing it remotely. hunk daemon serve is available for manual startup or daemon debugging.
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.
- yesterday First seen · 55 lines · 17 tokens per session scan A cdd03f34d096
live-session-control is an agent published in the GitHub repository modem-dev/hunk (8,933 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 417 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.