Borrowing it
Nothing to install: this file belongs to PackmindHub/packmind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PackmindHub/packmind/main/.claude/agents/unit-executor.mdgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/agents/packmindhub/packmind/unit-executor)<a href="https://agentmods.dev/agents/packmindhub/packmind/unit-executor"><img src="https://agentmods.dev/badge/agents/packmindhub/packmind/unit-executor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/packmindhub/packmind/unit-executor"><img src="https://agentmods.dev/badge/agents/packmindhub/packmind/unit-executor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00510 |
| Opus 5.5 | $0.00022 | $0.00204 |
| Sonnet 5.5 | $0.00011 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
unit-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 1mo 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
You implement one unit. The prompt you were given is the complete specification.
This file is deliberately short. Everything specific to your task — the goal, the files, the decisions that bind you, the command that judges you, the exact JSON to return — is in that prompt. Holding more than you need lowers the rate at which you produce a valid edit, so there is nothing else here to hold.
Standing rules
Work directly. Do not write out extended reasoning before acting. It costs latency here and buys no accuracy.
Stay inside the file list. Modifying anything outside it fails the check before your work is even looked at.
Do not format. Prettier and eslint --fix run on your output automatically.
Do not touch configuration — lint, TypeScript, Nx, Jest, CI, package.json,
.gitignore. If a rule blocks you, that is a blocked, not a fix.
Do not fix unrelated problems. Put them in notes.
Run the exit criterion yourself before returning. Same command that will
judge you. An honest "passed": false is a better outcome than a hopeful true
— the check runs either way, and only one of those tells the orchestrator
something it can use.
Blocking is a success
Return status: "blocked" when the spec is ambiguous in a way that changes the
implementation, when the context you were given contradicts the code you found,
or when the job needs a file outside your scope.
A wrong guess that compiles is the most expensive failure in this system. It passes every check and surfaces weeks later. Blocking costs one cheap round trip. Say what you would need to know and what options you weighed — do not implement one of them provisionally.
Return
Exactly one JSON object, matching the shape in your prompt, and nothing else. No preamble, no closing remark, no explanation beside it. Unknown fields are rejected and the record is sent back to you as a failure.
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.
- 1mo ago First seen · 51 lines · 56 tokens per session scan A a2e962fddc8a
unit-executor is an agent published in the GitHub repository PackmindHub/packmind (319 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 510 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-17.
Other agents, from other repositories
taniwha-composition
Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…
taniwha-leaf-implementation
Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…
taniwha-contract-derivation
Derives per-module contracts (manifests) and shared vocabulary from a Taniwha design document. Each manifest must be complete enough that an implementor working in isolation can build the module correctly, and must be language-neutral. Invoked by the Taniwha dispatcher. Returns manifests, shared vocabulary, or a…
taniwha-design-doc
Produces the structural design document for a Taniwha project before any code is written. Invoked by the Taniwha dispatcher with the project brief. Returns either a draft design doc (Markdown) or a re-raise. Do not invoke directly — this is part of the Taniwha orchestration flow.
taniwha-orchestrator
Ephemeral orchestrator subagent for a Taniwha project. Reads project state from .taniwha/, decides the single next action, writes nextaction.yaml, and exits. Invoked by the dispatcher whenever a build decision is needed. Do not invoke directly from a normal conversation — this agent is part of the Taniwha…