Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sxhmilyoyo/sundayhao-plugins/plugin install second-brainWrote 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/sxhmilyoyo/sundayhao-plugins/wdym)<a href="https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/wdym"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/wdym/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/sxhmilyoyo/sundayhao-plugins/wdym"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/wdym.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 | $0.00175 | $0.01116 |
| Opus 5.5 | $0.00070 | $0.00446 |
| Sonnet 5.5 | $0.00035 | $0.00223 |
| Haiku 4.5 | $0.00017 | $0.00112 |
Grade A, and why
wdym scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WDYM — What Do You Mean
Re-explain a stretch of this session's agent work to the person supervising it. The source material is the session itself: explain what actually happened here, never the general case.
Step 0: Load the profile
source "${CLAUDE_PLUGIN_ROOT}/skills/common/get_kb_path.sh" && KB_PATH=$(get_kb_path)
cat "$KB_PATH/rules/comprehension-profile.md"
The profile carries the person's calibration that is not already in their always-on instructions — register, analogy policy, native formats, daily-stack anchors, known confusion clusters — and overrides the generic defaults below. If the file is missing, use the defaults and offer once to compile a profile from the knowledge bank's reflections.
Calibration (generic defaults; the profile overrides)
- Peer register for a working engineer. Never a child's register.
- Prose at "80% of the way to ASD-STE100": short sentences, active voice, one term per concept, one idea per sentence. Soften rather than follow the spec strictly — strict STE measurably drops facts.
- One brief analogy may open; the in-context example is mandatory: the actual file, log line, or command from this session. An analogy without the in-context example is a non-answer.
- Anything with layers, roles, or directions gets a 2-axis table or a decision tree, not prose.
- Close substantial explanations with a trigger list: "you'll know X applies when …".
The ladder
Follow-ups escalate predictably. Answer the rungs that apply, and never leave the NEXT rung unaddressed — it is the question you will be asked anyway:
- What changed?
- Where does it come from? (file, config, upstream system)
- What is X? (term, acronym — define once, use it consistently after)
- Why this way? (the alternative considered, and why not)
- Prove it. (the verification evidence)
Format escalation
Start at rung 1; climb only while the point is not landing:
- Prose — 80%-STE, calibrated as above.
- Diagram — when the subject has layers, roles, directions, or flow. After drawing, restate every edge as a checkable sentence; a missing arrow silently claims "no dependency".
- Interactive HTML — one focused page, only when a static diagram cannot carry it (state spaces, before/after comparisons, things worth poking at). Reuse the show-me grammar.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed · +1 lines f0ff22105a10
- 12d ago First seen · 97 lines · 175 tokens per session scan A e20e9578a9c4
wdym is a skill published in the GitHub repository sxhmilyoyo/sundayhao-plugins (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 175 tokens to every session and 1,116 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
manage-desktop-flows
Manage and run Power Automate Desktop (RPA) flows and machine groups. Use when the user asks about desktop flows, RPA, or machine groups.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.