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 skills add Mark393295827/third-brain-v7-skills --skill behavior-designgit clone --depth 1 https://github.com/Mark393295827/third-brain-v7-skillsWrote 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/skills/mark393295827/third-brain-v7-skills/behavior-design)<a href="https://agentmods.dev/skills/mark393295827/third-brain-v7-skills/behavior-design"><img src="https://agentmods.dev/badge/skills/mark393295827/third-brain-v7-skills/behavior-design/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/skills/mark393295827/third-brain-v7-skills/behavior-design"><img src="https://agentmods.dev/badge/skills/mark393295827/third-brain-v7-skills/behavior-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01004 |
| Opus 5.5 | $0.00012 | $0.00402 |
| Sonnet 5.5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
behavior-design 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior Design
<skill_contract> Actor, desired outcome, current behavior, context, constraints, baseline evidence, and review horizon. An agency-preserving HAS behavior system with cues, effort levels, SOP, measures, recovery, and review cadence. The target behavior is observable, runnable on a low-motivation day, evidenced, and assigned one review owner. <non_goals>Coercion, unsupported identity claims, vague motivation advice, or optimizing lagging outcomes without behaviors.</non_goals>
Convert an outcome into the smallest observable behavior system that can survive low-motivation days. Preserve agency; optimize the environment before blaming the actor.
Usage Template
Provide: desired outcome, actor, context, current behavior, constraints, review horizon, and available evidence. Optional: failed attempts and environmental cues.
Workflow
- Restate the outcome as an observable change, not an identity label.
- Establish baseline frequency, friction, trigger context, and hard constraints.
- Separate controllable behavior from lagging outcome.
- Set one review horizon and one owner.
<unknowns_gate>
Classify unknowns as known, probeable, testable, or blocked. If actor, target behavior, or safety boundary is absent, return NEEDS_INPUT with one minimal question. A reversible assumption is allowed only when labeled and paired with a same-cycle test.
</unknowns_gate>
Build the HAS sequence:
- H1 Goal: translate the outcome into one leading behavior and one lagging measure.
- H2 Habit: define anchor, cue, location, and three effort levels: minimum (about 2 minutes), normal, and stretch.
- H3 SOP: write
trigger -> action -> evidence -> recovery -> stopso a missed run has a next move. - H4 Review: select a cadence; compare planned versus observed behavior and change one variable only.
- H5 Identity: use evidence-based reinforcement: “I am becoming X because I repeatedly did Y,” never unsupported affirmation.
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 · 99 lines · 29 tokens per session scan A 7f4425f00215
behavior-design is a skill published in the GitHub repository Mark393295827/third-brain-v7-skills (141 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,004 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
obsidian-ai-setup
Bootstrap an Obsidian vault with the AI Pro Obsidian Plugin. Creates the complete vault structure, system files, Obsidian configuration, memory system, hooks, and output styles, then runs personalized onboarding to tailor the workspace to the user. Uses a single universal structure with no mode selection. Trigger when…
apply
A browser-based job application workflow for submitting applications through services such as Ashby, Greenhouse, Lever, and Hacker News. It uses prepared candidate information, answers, job links, and cover letters.
screenpipe-api
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved…
retro-lost
Run a retrospective for an abandoned agent session (untouched for over 24 hours, never closed with a retro): rebuild context cold from the transcript, list what was built, sort Keep/Drop/Try and file the durable parts. Use from a nightly routine or on demand. Triggers: /retro-lost, retro for an abandoned session.
pkm-session-end
Use when wrapping up a work session — creates devlog entry, captures undocumented decisions/research/debugging, audits link health of session work, and updates project index. Primarily used via the pkm-capture agent.
nsr
A routine for starting a new, visible coding-agent session automatically through a scheduled task, so it appears in the recent-session list without someone pressing a start button.