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 sqlew-io/sqlew-plugin --skill sqlew-decision-formatgit clone --depth 1 https://github.com/sqlew-io/sqlew-pluginWrote 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/sqlew-io/sqlew-plugin/sqlew-decision-format)<a href="https://agentmods.dev/skills/sqlew-io/sqlew-plugin/sqlew-decision-format"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-decision-format/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/sqlew-io/sqlew-plugin/sqlew-decision-format"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-decision-format.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.01129 |
| Opus 5 | $0.00024 | $0.00564 |
| Sonnet 5 | $0.00010 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
sqlew-decision-format 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Mode: Decision & Constraint Recording
When including decisions or constraints in your plan, use the following format.
They will be auto-detected on ExitPlanMode (Claude Code), exit_plan_mode approval (Grok Build),
or Codex Plan mode session stop, and registered via the hook queue in sqlew.
Grok Build: Write these blocks directly in plan.md. Hook stdout injection is not available;
sqlew seeds a template section on plan.md via file side-effects (enter plan / prompt / post-edit).
Approving the plan without filled blocks is denied by default (hooks.grok_require_patterns).
This skill remains the reference for field meanings and what to record.
Codex: Write these blocks in the plan output during collaboration Plan mode.
Extraction runs from the session transcript on Stop.
What to Record (and What NOT to Record)
sqlew stores facts that cannot be re-derived from the code. Before writing a 📌 Decision or 🚫 Constraint block, apply this filter:
Record:
- Choices where alternatives were considered and rejected — and WHY they lost
- Constraints imposed from outside the code: business rules, compliance, customer commitments, team agreements
- Non-obvious tradeoffs: workarounds for upstream bugs, deliberate deviations from the idiomatic approach (performance, past incidents)
- Anything a future agent might "helpfully" undo because the reason is invisible in the code
Do NOT record:
- Facts derivable from the code itself (dependencies, file structure, framework or library in use)
- Implementation details that can change freely without consequence
- Temporary or experimental choices that are not yet settled
- Restatements of what the code already says
Rule of thumb: if a future AI agent reading only the code would reach the same conclusion, skip it. If it would guess the reason wrong — record it with the WHY.
📌 Decision: [hierarchical/key]
Record decisions using this format:
### 📌 Decision: [key/path]
- **Value**: Description of the decision
- **Layer**: presentation | business | data | infrastructure | cross-cutting
- **Tags**: tag1, tag2 (optional)
- **Rationale**: Why this decision was made (strongly recommended — the WHY is the part future agents cannot infer from code)
- **Alternatives**: Option A, Option B (comma-separated; record what was rejected)
- **Tradeoffs**: Pros and cons description (optional)
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.
- 10d ago First seen · 128 lines · 49 tokens per session scan A 783be8b144bd
sqlew-decision-format is a skill published in the GitHub repository sqlew-io/sqlew-plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,129 once invoked, about $0.0002 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
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
computer-use
Control local desktop applications through Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.