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 MichaelYcJo/SpecSeal --skill learngit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWrote 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/michaelycjo/specseal/learn)<a href="https://agentmods.dev/skills/michaelycjo/specseal/learn"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/learn/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/michaelycjo/specseal/learn"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/learn.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 | $0.00085 | $0.00445 |
| Opus 5.5 | $0.00034 | $0.00178 |
| Sonnet 5.5 | $0.00017 | $0.00089 |
| Haiku 4.5 | $0.00009 | $0.00044 |
Grade A, and why
learn 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
learn, write down only what a search cannot return
Most of what a session discovers is recoverable: the code holds it, git holds it, a search answers it in five minutes. What is not recoverable is the thing that cost hours and leaves no trace, such as the dependency quirk or the reason an abstraction is shaped that way. Record that and nothing else.
Save Criteria (must meet ALL)
- Non-Googleable: no five-minute search finds the answer
- Project-specific: tied to this codebase or setup
- Hard-won: it took real debugging effort
- Actionable: it includes specific files, lines, code
What to Save
- Bug patterns unique to this project
- Non-obvious configuration requirements
- Architectural decisions and their reasons
- Dependency quirks and workarounds
- Performance pitfalls discovered through profiling
What NOT to Save
- General programming knowledge
- Standard library usage
- Anything in official docs
- Temporary workarounds (save the real fix instead)
Storage
Save to: ~/.claude/projects/<project>/memory/
- Use semantic filenames:
auth-session-quirk.md,db-connection-pool.md - Keep each file focused on one insight
- Update existing files rather than creating duplicates
Format
# [Short descriptive title]
## Problem
[What went wrong]
## Root Cause
[Why it happened, specific to this project]
## Solution
[What fixed it, with file paths and code]
## Prevention
[How to avoid this in the future]
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 Changed f0fa15740fc4
- 2mo ago First seen · 62 lines · 85 tokens per session scan A c41748e66262
learn is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 445 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
performance-audit
Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…
init
Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…
pocket-init
Onboards an existing project onto Pocket by scanning its local configuration, writing a merge-safe project guide, and optionally calibrating a local Pocket Education learner profile. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "generate AGENTS.md", or "enable education…
PlanGate 決定論的 GC 判定
A rule-based checker that decides whether stored files, logs, and other review records should be kept or removed. It applies retention limits and safety exceptions to a supplied file list.
Closure Scope Retention Guard
Detects long-lived objects (caches, listeners, singletons) that capture an entire enclosing scope via closures/environment capture, keeping large arrays or buffers alive, and proposes copying only the needed fields.