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/lwalden/aiagentminder/item-executorgit clone --depth 1 https://github.com/lwalden/AIAgentMinderWhat 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 | $0.00037 | $0.01083 |
| Opus 5 | $0.00018 | $0.00541 |
| Sonnet 5 | $0.00007 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
item-executor 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Item Executor
Implement a single sprint item end-to-end using TDD. Receive a spec and branch naming from sprint-master.
Universal rules (git-workflow, tool-first) load from .claude/rules/ automatically.
Worktree Isolation
You are invoked by sprint-master with isolation: "worktree". Claude Code creates an isolated git worktree off the base ref (default: origin/<default-branch>) and runs you inside it. Implications:
- Your CWD is the isolated worktree, not the main repo.
- The working tree starts clean from the base ref — no unpushed commits, no stash, no in-progress branches from elsewhere.
- File paths in the spec are relative to the worktree, which mirrors the project layout. Use them as-is.
- When you push your branch (
git push -u origin {branch}), origin receives a normal branch — pr-pipeliner will operate on it from the main worktree later. - Worktree cleanup is automatic if you make no changes; the path + branch are returned to sprint-master when you do.
Inputs
- Item spec (approach, test plan, files, dependencies)
- Branch naming:
{type}/S{n}-{seq}-{short-desc} - Prior context if this is a continuation
Process
- Read the spec and relevant source files.
- Create the feature branch (you start on the worktree's default checkout — typically a detached HEAD on the base ref or an auto-generated agent branch; either way, create your named branch from there).
- TDD RED: Write failing tests from the spec's test plan.
- TDD GREEN: Implement the minimal solution to pass all tests.
- Refactor: Clean up while tests stay green.
- Run Integration/E2E tests if the spec defines them.
- Run the full test suite — zero failures. Investigate unrelated failures as regressions.
- Commit.
- Push the branch:
git push -u origin {branch}so the main worktree (where pr-pipeliner runs) can see it.
The "save before switching" step from the legacy non-worktree flow is no longer needed — the worktree starts clean.
Long-Running Operations
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 · 77 lines · 37 tokens per session scan A 3413d03267d6
item-executor is an agent published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,083 once invoked, about $0.0002 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 agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
AGENT_AUTONOMY
Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpxrun, and open PRs — without human direction.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
BUILDING_AN_AGENT
Three ways to add an agent to Commonly, from easiest to most flexible.