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 lukacf/meerkat --skill skill-discovery-workflowgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/skill-discovery-workflow)<a href="https://agentmods.dev/skills/lukacf/meerkat/skill-discovery-workflow"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/skill-discovery-workflow.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00450 |
| Opus 5 | $0.00010 | $0.00225 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
skill-discovery-workflow 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 7d 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.
What it actually says
Skill Discovery Workflow
Use skills when the available skill inventory contains domain guidance that would improve the current turn. Skills are explicit instruction manuals; they are discoverable by default but not automatically injected unless a session or turn asked for them.
Operating Rules
- Use
browse_skillswhen the inventory is in collection mode, when the user mentions a domain, or when you suspect a built-in companion skill exists for a tool family. - Use
load_skillwith a typed builtinSkillKeywhen you need the full operating guidance before calling a tool family. On the wire, pass thesource_uuidandskill_namefields returned bybrowse_skills; do not synthesize a slash-delimited identifier. - Use
skill_list_resourcesandskill_read_resourcefor supporting files a skill exposes. Read only the resources needed for the current workflow. - Use
skill_invoke_functiononly for a function explicitly exposed by the selected skill. Itsargumentsmust be a JSON object, and its output is wire-opaque skill-owned JSON. - Treat tool descriptions as schema and capability summaries. Treat companion skills as the source for when, how, and why to use a tool family.
- Respect capability gating. If a skill is absent, continue with the tools that are actually available instead of assuming the capability exists.
- Do not preload broad skills just in case. Load only the skill needed for the current workflow.
- Source identity can be remapped by the runtime. Continue with the canonical key returned by load/resource/function operations rather than caching an old source UUID as permanent identity.
Companion Skills
Companion skills are embedded skills owned by a Meerkat crate or tool family.
They are gated by requires_capabilities and teach agent behavior for a
capability such as WorkGraph, Schedule, shell, memory, comms, hooks, or builtin
utilities.
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.
- 7d ago First seen · 44 lines · 21 tokens per session scan A c06c062a3ad1
skill-discovery-workflow is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 450 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
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…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
agent-reproduce-feature
Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.