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-plan-guidancegit 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-plan-guidance)<a href="https://agentmods.dev/skills/sqlew-io/sqlew-plugin/sqlew-plan-guidance"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-plan-guidance/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-plan-guidance"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-plan-guidance.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 | $0.00041 | $0.02092 |
| Opus 5 | $0.00020 | $0.01046 |
| Sonnet 5 | $0.00008 | $0.00418 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
sqlew-plan-guidance 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 11d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REQUIRED: Suggest Search BEFORE Planning
CRITICAL: Before writing any plan, you MUST search for related context.
Step 1: Extract keywords from the user's task (e.g., migration, auth, database)
Step 2: Run suggest search:
suggest { action: "by_context", key: "<keyword>", tags: ["<relevant-tags>"] }
suggest { action: "by_context", target: "constraint", text: "<topic>" }
Step 3: Include results in plan (MANDATORY section):
## Related Context (from sqlew)
### Past Decisions
| Key | Value | Score |
|-----|-------|-------|
| path/to/decision | description | 85 |
> If empty: "No related decisions found for: <keywords>"
### Applicable Constraints
- **[category]**: constraint text (Priority: high)
> If empty: "No constraints found for: <keywords>"
FAILURE TO INCLUDE "Related Context" SECTION = INVALID PLAN
REQUIRED: Conflict Handling (Plan Overturns an Existing Decision)
If a decision found by the suggest search contradicts your new plan:
- Never silently ignore it. List the conflicting decision in the "Related Context" section and state that the plan overturns it.
- Read its context first:
decision { action: "get", key: "<key>", include_context: true }— the old rationale may encode a constraint (upstream bug, compliance, past incident) your plan has not considered. - Same key, new direction: register the new decision under the same key (sqlew keeps history). Explain in Rationale why the previous decision no longer applies.
- Different key: register the new decision, then deprecate the old one:
decision { action: "set", key: "<old-key>", value: "Superseded by <new-key>", status: "deprecated" }
A stale decision that contradicts the code is worse than no decision — it becomes misinformation. Deprecating on reversal keeps the database trustworthy.
Grok Build Notes (v5.2+ / multi-trigger template v5.5+)
CRITICAL for Grok Build: UserPromptSubmit hook stdout is ignored (passive hook).
Format guidance is delivered via this skill and sqlew-decision-format.
The 📌/🚫 template block is written to plan.md as a file side-effect (not stdout).
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.
- 11d ago First seen · 216 lines · 41 tokens per session scan A cd64cf064a7c
sqlew-plan-guidance is a skill published in the GitHub repository sqlew-io/sqlew-plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,092 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.