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/vibecodingnights/loop-engineering/hypergraphnpx skills add VibeCodingNights/loop-engineering --skill hypergraphgit clone --depth 1 https://github.com/VibeCodingNights/loop-engineeringWhat 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 | $0.00221 | $0.03363 |
| Opus 5 | $0.00111 | $0.01682 |
| Sonnet 5 | $0.00044 | $0.00673 |
| Haiku 4.5 | $0.00022 | $0.00336 |
Grade A, and why
task-hypergraph 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/GOAL.template.md 2.0 KB
- assets/node.template.md 5.9 KB
- assets/topology.template.html 11 KB
- assets/workflow.template.js 22 KB runs code
- README.md 6.3 KB
- references/gate-menu.md 6.4 KB
- references/review-personas.md 7.2 KB
- scripts/char_guard.py 2.9 KB runs code
- scripts/codex_exec.sh 4.7 KB runs code
- scripts/frontier.py 6.3 KB runs code
- scripts/install_stop_hook.sh 14 KB runs code
- scripts/scaffold.sh 13 KB runs code
- scripts/validate.py 4.4 KB runs code
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 · 117 lines · 221 tokens per session scan A b7e6755d1ff9
task-hypergraph is a skill published in the GitHub repository VibeCodingNights/loop-engineering (3 stars, last pushed 1mo ago), with no licence file. It adds 221 tokens to every session and 3,363 once invoked, about $0.0011 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
grace-cli
Operate the GRACE 4 CLI for .grace linting, status, module navigation, verification navigation, and file-local semantic markup.
grace-execute
Execute an approved GRACE 4 GraceChangePlan in sequential or parallel-safe mode with recovery-aware preflight and centralized durable apply.
grace-init
Bootstrap a Full GRACE 4 project by creating the canonical .grace context, graph, verification, and changes skeleton.
grace-migrate
Agent-applied GRACE 3 to GRACE 4 migration workflow. CLI validates the result but does not convert or delete files.
grace-plan
Read an approved GRACE 4 GraceChangeSpec and optional design context, then create a GraceChangePlan with assertions, scopes, tasks, and verification gates.
grace-verification
Design and maintain GRACE 4 verification entries, commands, scenarios, markers, and assertion evidence under .grace/verification.