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/implementnpx skills add AgentureHQ/agenture-loop --skill implementgit 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 | $0.00041 | $0.03011 |
| Opus 5 | $0.00020 | $0.01505 |
| Sonnet 5 | $0.00008 | $0.00602 |
| Haiku 4.5 | $0.00004 | $0.00301 |
Grade A, and why
implement 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement (/agn:implement <level> <id>)
Arguments
| Position | Variable | Value |
|---|---|---|
$0 |
level | task, feature, or epic |
$1 |
id | Task file path (for task) or slug (for feature / epic) |
Argument validation
If $0 is missing, stop and ask:
"What level — task, feature, or epic?"
If $0 is not one of task, feature, epic, stop and list the valid set.
If $1 is missing, stop and ask the user for the task path or slug.
Lifecycle actions — always via taskman.sh
All file moves and status transitions go through scripts/taskman.sh. Do not mv task files or edit YAML status by hand.
./scripts/taskman.sh move <task-path> active # backlog → active
./scripts/taskman.sh move <task-path> done # active → done
./scripts/taskman.sh feature close <slug> # close feature when all tasks done
./scripts/taskman.sh epic close <slug> # close epic when all features done
Design gap escalation protocol
When /agn:implement task detects a meaningful design gap during detailed design (missing scope detail, ambiguous acceptance criterion, undefined interface contract), it halts, writes a gap-log entry, and routes the user to the upstream skill that should address it. This protocol preserves the Design/Implementation separation: implementers do not silently improvise design.
Gap-log file format
Gap-log files live at tasks/gaps/<YYYYMMDD-HHMMSS>_<task-slug>.md. One file per detected gap. Written via the Write tool directly — not through taskman.sh (gaps are observability records, not lifecycle units).
Frontmatter:
---
detected: 2026-05-26T15:23:00Z # ISO 8601 with timezone
task: <task-slug>
task_path: tasks/active/YYYYMMDD_<slug>.md
suspected_level: task | feature | epic | architecture
status: open | resolved
---
Body sections (all required):
# Gap: <one-line description>
## Description
<what design information is missing or ambiguous>
## Detection context
<which step of /agn:implement task surfaced this; what the implementer was trying to do at the moment of detection>
## Suspected upstream
<which level needs revision; which skill the user should invoke>
## Resolution
<filled when the gap is marked resolved; left empty initially>
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 · 287 lines · 41 tokens per session scan A ee2da9ddfc1d
implement is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 3,011 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'.