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/dvnghiem/flowdeck/decision-tracenpx skills add DVNghiem/FlowDeck --skill decision-tracegit clone --depth 1 https://github.com/DVNghiem/FlowDeckWrote 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/dvnghiem/flowdeck/decision-trace)<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/decision-trace"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/decision-trace.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.01940 |
| Opus 5 | $0.00015 | $0.00970 |
| Sonnet 5 | $0.00006 | $0.00388 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
decision-trace 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 4d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Trace
Every non-trivial edit should be recorded in ~/.fd-plan/<slug>/.codebase/DECISIONS.jsonl. This creates an append-only audit trail that makes code review and debugging faster.
When to Record a Decision
Record when:
- Editing a file that affects behavior (not just formatting/comments)
- Choosing between two or more implementation approaches
- Making an assumption about a requirement
- Fixing a bug or regression
- Changing an API contract or schema
How to Record
Use the decision-trace tool:
{
"action": "record",
"entry": {
"id": "auth-refactor-2024-05-01",
"file_path": "src/services/auth.ts",
"change_type": "edit",
"rationale": "Refactored token validation to use constant-time comparison to prevent timing attacks",
"evidence": [
"OWASP: timing attacks on string comparison",
"Prior failure: auth-timing-2024-03 in FAILURES.json"
],
"assumptions": [
"Token format remains base64-encoded JWT",
"Redis cache is available for token blacklist"
],
"alternatives_considered": [
"Keep string comparison (rejected: timing attack risk)",
"Move validation to edge (rejected: adds latency)"
],
"risk_level": "medium",
"agent": "backend-coder"
}
}
Automatic Recording
The decision-trace-hook auto-records a minimal entry for every write/edit. The full entry (with rationale, evidence, assumptions) should be added by the agent explicitly using the tool above.
Querying Decisions
// Get all decisions for a file
{ "action": "get_for_file", "file_path": "src/services/auth.ts" }
// Get all high-risk decisions
{ "action": "query", "query": { "risk_level": "high", "limit": 10 } }
Decision Evolution
Decisions are not static. They change as requirements shift, new evidence appears, or better alternatives emerge. Track the full lifecycle:
alternatives_considered
List every option evaluated and why it was rejected or accepted. This prevents re-litigating old choices.
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.
- 4d ago First seen · 210 lines · 29 tokens per session scan A 6015902f3296
decision-trace is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 1,940 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
deepwork
High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.