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 skills/agenturehq/agenture-loop/plannpx skills add AgentureHQ/agenture-loop --skill plangit clone --depth 1 https://github.com/AgentureHQ/agenture-loopWhat 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 | $0.00043 | $0.01181 |
| Opus 5 | $0.00022 | $0.00590 |
| Sonnet 5 | $0.00009 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
plan 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan (/agn:plan <level>)
Arguments
| Position | Variable | Value |
|---|---|---|
$0 |
level | epic or feature |
Argument validation
If $0 is missing, stop and ask:
"What level — epic or feature?"
If $0 is not one of epic, feature, stop and list the valid set.
Dispatch
Read $0. Run exactly one of the branches below.
$0 = epic
Preconditions
The epic file must exist under tasks/epics/. If it does not, stop and direct the user to /agn:define epic.
Workflow
-
Locate — Confirm the epic slug. Read the epic file and its current
## Linked features. List the existing feature files undertasks/features/that carryepic: <slug>. -
Identify the decomposition gap — Ask the user what needs to change: a missing feature, an obsolete feature, reordering, splitting a feature, merging two. Surface what is currently in
donevsactivevsbacklogso the user knows what is in flight. -
Delegate to the Planner. Invoke via the Agent tool with
subagent_type: plannerand the following brief:level=epicmode=refinetitle=<existing epic file path>initial_scope=plan-only — <user description of decomposition change>; existing features: <list>upstream=<docs/vision.md, docs/spec.md, docs/architecture.md if relevant>
The Planner returns a
## Decompositiondelta — features to add, remove, or re-order — plus a one-sentence rationale. It does not touch the epic body (that's/agn:design epic). -
User review — Show the proposed feature changes. Iterate until approved.
-
Persist —
- For each new feature: invoke
/agn:define feature --epic <slug>(ortaskman.sh new feature --epic <slug>if the user provides bodies inline). - For each obsolete feature still in
backlog: confirm with the user, thentaskman.sh discard <path>. - For ordering changes: edit the epic's
## Linked featureslist in place via the Edit tool. - Features already in
activeordoneare not modified; surface them in the report.
- For each new feature: invoke
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 · 107 lines · 43 tokens per session scan A ea1a7c3f716b
plan is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,181 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 skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.