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 commands/dokkabei97/forged-claude-code/decision-loggit clone --depth 1 https://github.com/Dokkabei97/forged-claude-codeWrote 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/commands/dokkabei97/forged-claude-code/decision-log)<a href="https://agentmods.dev/commands/dokkabei97/forged-claude-code/decision-log"><img src="https://agentmods.dev/badge/commands/dokkabei97/forged-claude-code/decision-log.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 | $0.00025 | $0.01266 |
| Opus 5 | $0.00013 | $0.00633 |
| Sonnet 5 | $0.00005 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
decision-log 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decision-log - Decision Record Generator
Triggers
- When a significant decision is made (technical, product, business)
- When someone asks "why did we decide to..."
- When documenting the rationale behind a choice for future reference
Usage
/decision-log [decision title]
/decision-log "Use Supabase instead of Firebase"
/decision-log --list # Show all recorded decisions
/decision-log --review [ID] # Review a past decision
Behavioral Flow
Phase 1: Determine Decision Context
Identify what type of decision is being recorded:
| Category | Examples |
|---|---|
| Technical | Stack choice, architecture pattern, library selection |
| Product | Feature priority, UX approach, pricing model |
| Business | Hiring, partnership, market focus |
| Process | Workflow change, tool adoption, meeting cadence |
Phase 2: Gather Decision Details
Prompt for or extract from conversation:
- Title: One-line summary of the decision
- Context: What problem or situation prompted this decision?
- Options Considered: What alternatives were evaluated?
- Decision: What was chosen?
- Rationale: Why was this option selected?
- Consequences: What are the expected outcomes and trade-offs?
Phase 3: Generate Decision Record
# DR-[NNNN]: [Decision Title]
| Field | Value |
|-------|-------|
| **Date** | YYYY-MM-DD |
| **Status** | Proposed / Accepted / Deprecated / Superseded |
| **Category** | Technical / Product / Business / Process |
| **Deciders** | [Names/Roles] |
| **Supersedes** | DR-[NNNN] (if applicable) |
## Context
[2-3 sentences describing the situation, problem, or opportunity that
prompted this decision. Include constraints and requirements.]
## Options Considered
### Option A: [Name]
- **Pros**: [advantages]
- **Cons**: [disadvantages]
- **Cost/Effort**: [estimate]
### Option B: [Name]
- **Pros**: [advantages]
- **Cons**: [disadvantages]
- **Cost/Effort**: [estimate]
### Option C: [Name] (if applicable)
- **Pros**: [advantages]
- **Cons**: [disadvantages]
- **Cost/Effort**: [estimate]
## Decision
**We chose Option [X]: [Name].**
## Rationale
[Why this option was selected over others. Be specific about the
deciding factors and how they mapped to our current constraints.]
## Consequences
### Positive
- [Expected benefit 1]
- [Expected benefit 2]
### Negative / Trade-offs
- [Accepted trade-off 1]
- [Accepted trade-off 2]
### Risks
- [Risk 1] — Mitigation: [plan]
## Review Date
[When should this decision be revisited? e.g., "After reaching 10K users"
or "Q3 2026" or "When [condition] changes"]
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 · 179 lines · 25 tokens per session scan A 3cb62af00fb1
decision-log is a command published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 1,266 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 2026-08-31.
Other commands, from other repositories
media-extract-pdf
Gemini-only command that extracts structured data from PDFs — invoices, tables, forms — as JSON, CSV, markdown or text.
media-organize-files
Gemini-only command that renames and refiles a directory by analysing file contents rather than extensions, behind a dry-run plan.
media-sketch-to-code
Gemini-only command that turns sketches, wireframes and mockups into framework-specific component code or Mermaid diagrams.
media-analyze-audio
Gemini-only command that classifies audio as speech, music, ambient or mixed and reports mood, segments and technical quality.
media-analyze-images
Gemini-only command that finds images in a directory, describes their visual content and suggests content-based filenames.
media-analyze-video
Gemini-only command that breaks a video into scenes and reports setting, subjects, actions, dialogue and visual style per scene.