Borrowing it
Nothing to install: this file belongs to notactuallytreyanastasio/deciduous. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/notactuallytreyanastasio/deciduous/main/.opencode/skills/pulse/SKILL.mdgit clone --depth 1 https://github.com/notactuallytreyanastasio/deciduousWrote 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/notactuallytreyanastasio/deciduous/pulse)<a href="https://agentmods.dev/skills/notactuallytreyanastasio/deciduous/pulse"><img src="https://agentmods.dev/badge/skills/notactuallytreyanastasio/deciduous/pulse/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/notactuallytreyanastasio/deciduous/pulse"><img src="https://agentmods.dev/badge/skills/notactuallytreyanastasio/deciduous/pulse.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 | $0.00014 | $0.00585 |
| Opus 5.5 | $0.00006 | $0.00234 |
| Sonnet 5.5 | $0.00003 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
pulse 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pulse
Map the current model as decisions. No history, just now.
Step 1: Get current state
deciduous pulse
Review the report: active goals, coverage gaps, orphan nodes. This tells you what's already mapped and what needs attention.
Step 2: Pick a scope
What part of the system are you taking the pulse of?
- A feature ("Suspense fallback behavior")
- A subsystem ("Authentication")
- A boundary ("API request lifecycle")
Step 3: Ask "What decisions define this?"
Read the code. For the thing you're scoping, ask:
"What design questions had to be answered for this to work?"
Not implementation questions ("which library?") - model questions ("what's the behavior?")
Step 4: Build the goal -> options -> decisions
# Create the root goal
deciduous add goal "<Scope>: <Core question>" -c 90
# Add options (possible approaches from the goal)
deciduous add option "<Possible approach>" -c 85
deciduous link <goal> <option> -r "possible_approach"
# When an option is chosen, create a decision
deciduous add decision "Chose <approach>" -c 90
deciduous link <option> <decision> -r "chosen"
If a question is still open, leave it as option nodes without a decision.
Step 5: Review
deciduous pulse
deciduous pulse --summary
deciduous serve
Check for Supporting Documents
deciduous doc list <goal_id>
deciduous doc attach <goal_id> docs/architecture.png -d "Current architecture"
Decision Criteria
- Worth capturing? Does it define BEHAVIOR, not implementation?
- How deep? Stop when decisions become implementation details
- Option vs Decision? Option = possible approach. Decision = choosing which option.
Connecting to History
Pulse gives you the "Now". For history, run /narratives then /archaeology.
Working Alongside Other Agents
If other agents work on this at the same time (one narrative each, say), split the work and hand off on the deciduous message board, never in a scratch file: post with deciduous board post --as <label> -s "..." -m "@other ..." (or the post_message MCP tool), read deciduous board read --unanswered <label> before you start and before you finish, and answer with --reply-to <id>.
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 Changed · +4 lines 44a080045d7b
- 2mo ago First seen · 76 lines · 14 tokens per session scan A 82ddb615f712
pulse is a skill published in the GitHub repository notactuallytreyanastasio/deciduous (169 stars, last pushed 13d ago), licensed Apache-2.0. It adds 14 tokens to every session and 585 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.
pulse compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pulsenotactuallytreyanastasio/deciduous | Skill | 169 | 13d ago | Apache-2.0 | A | 14 | OpenCode |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |