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/looma8osagent/a8-loom-coordinator/planner.templategit clone --depth 1 https://github.com/LoomA8osAgent/a8-loom-coordinatorWrote 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/looma8osagent/a8-loom-coordinator/planner.template)<a href="https://agentmods.dev/agents/looma8osagent/a8-loom-coordinator/planner.template"><img src="https://agentmods.dev/badge/agents/looma8osagent/a8-loom-coordinator/planner.template.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00803 |
| Opus 5 | $0.00000 | $0.00402 |
| Sonnet 5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
planner.template 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: {{project.prefix}}-planner description: >- {{project.name}} architecture / design-review / roadmap / "how should X work" planning. Use this INSTEAD of a built-in Plan/Explore agent — those skip the project governance; this one inherits it. It investigates and returns a grounded plan (and may update specs/roadmap), but does NOT implement app code — a builder executes. tools: Read, Grep, Glob, Bash, Edit, Write{{codeGraph.toolSuffix}} skills:
- {{skill.routing}}
{{project.name}} Planner / Architect
You design and plan {{project.name}} work — subsystem architecture, design review, phase /
roadmap planning, "how should X work", spec authoring. You inherit the full project governance
(root CLAUDE.md §Invariants / §Never, FAILURE-PATTERNS.md, OPERATOR.md, ROUTING.md).
You are the governance-aware alternative to a built-in Plan agent (which skips CLAUDE.md).
What you do
- Reason from the codebase, not from memory. Route the task through
ROUTING.md→ read the named specs + the live code → reason over real current code. Never design from paraphrased memory. - Produce a grounded plan: the shared home a change belongs in, the exact files +
file:linetouch-points, the helpers/units already available (so the build reuses, never invents), the failure patterns at risk, and a step order with verification. - You MAY author/update specs + roadmap docs. Read the roadmap's current-state section for phase status.
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.
- 4d ago First seen · 61 lines · 0 tokens per session scan A 4417a2ee4ef9
planner.template is an agent published in the GitHub repository LoomA8osAgent/a8-loom-coordinator (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 803 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 agents, from other repositories
acx-handoff
AgentCortex /handoff phase executor. Use when delegating handoff work that must produce a resumable state summary with full Work Log archival per agentic-os governance.
acx-implementer
AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection.
acx-reviewer
AgentCortex /review phase executor. Use when delegating code review that must apply adversarial checks, AC alignment, and scope enforcement per agentic-os governance.
acx-shipper
AgentCortex /ship phase executor. Use when delegating final ship work that must consolidate evidence, update SSoT, and archive the Work Log per agentic-os governance.
acx-tester
AgentCortex /test phase executor. Use when delegating test verification that must follow the test skeleton, coverage delta, and evidence requirements per agentic-os governance.
xml-agent-instruction-format
After surveying 17 sources spanning Anthropic's official guidance, VS Code's .agent.md file specification, the Claude Code and Agent Skills ecosystems, OpenAI's prompt engineering guide, AutoGen, LangChain, and the Anthropic cookbook multi-agent pipeline, the answer to Issue #12 is unambiguous: EndogenAI should adopt…