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 agentmods add skills/jlifyio/wyx/conceptnpx skills add jlifyio/wyx --skill conceptgit clone --depth 1 https://github.com/jlifyio/wyxWhat 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 | $0.00073 | $0.02551 |
| Opus 5 | $0.00036 | $0.01275 |
| Sonnet 5 | $0.00015 | $0.00510 |
| Haiku 4.5 | $0.00007 | $0.00255 |
Grade A, and why
concept 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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bounded Concept Design
Generate a concept specification — a structured description of a module that serves as compressed context for code generation. A concept spec replaces reading 200+ lines of implementation with a 30-line bounded description of what the module IS.
How to interpret $ARGUMENTS
Determine the mode from the argument:
- Path to directory/file (e.g.
src/lib/server/auth/): Retrofit mode — read the existing code and propose a concept spec that describes what is already there. Flag any boundary violations you find (imports from other modules' internals, shared mutable state, etc.) - Feature description (e.g.
Portfolio tracking with watchlists): Greenfield mode — design a new concept spec from the description. Enforce decomposition: if the feature has multiple independent purposes, split into multiple concepts. driftorcheck(with optional path, e.g.drift src/lib/server/): Drift detection mode — compare existing CONCEPT.md/PIPELINE.md specs against current code. Produce a structured drift report showing what has diverged.- No arguments: Discovery mode — analyze the project structure and propose which modules should have concept specs. List each candidate with a one-line purpose. Do NOT generate full specs; ask the user which ones to elaborate. After listing concept candidates, if the project has data transformation patterns or cross-concept coordination, briefly note that
/wyx:pipelineand/wyx:syncare available for those patterns.
Concept Spec Format
Write the spec as a CONCEPT.md file placed next to the implementation code (e.g. src/lib/server/auth/CONCEPT.md).
Use this exact structure:
# concept: [Name] [TypeParam]
## purpose
[Single sentence: what this module does and for whom]
## state
- [field]: [TypeParam] -> [type]
- [field]: [TypeParam] -> [type]
## actions
### [action-name] [input1: Type, input2: Type] => [output: Type]
[1-3 lines: what this action does, when it succeeds, when it fails]
### [action-name] [input1: Type] => [result: Type] | [error: String]
[behavior description with error cases as separate output patterns]
## operational principle
after [action]([args])
=> [expected output]
then [action]([args])
=> [expected output]
[This is simultaneously a behavioral contract and a test seed.
Write scenarios that define correct behavior. Multiple scenarios OK.]
## interactions
[Optional. How this concept coordinates with others.]
- when [ExternalConcept/action] completes, [this concept/action] should follow
Use `ConceptName.actionName()` syntax for cross-concept references — these are validated during drift detection.
## dependencies
[Optional. External concepts this module depends on.]
- [ExternalConcept]: [what this concept needs from it]
## known coupling
[Optional. Intentional cross-concept data access that bypasses action interfaces.
Each entry: resource, access pattern, reason, and resolution status.]
- [ExternalConcept/resource]: [access pattern] — reason: [why] — status: keep|refactor|defer
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.
- 2d ago First seen · 175 lines · 73 tokens per session scan A f08f19d50ca2
concept is a skill published in the GitHub repository jlifyio/wyx (3 stars, last pushed 24d ago), licensed MIT. It adds 73 tokens to every session and 2,551 once invoked, about $0.0004 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
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.
truecourse-list
List TrueCourse violations found in this repository.
code-quality-review
Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查, 可维护性审查, or comments about whether the change stays easy to…
optimization-audit
Comprehensive optimization audit with two modes and a single tier. Planning mode designs performance strategy, capacity planning, and scaling architecture. Audit mode scans code and infrastructure for performance anti-patterns, inefficient algorithms, N+1 queries, missing caching, concurrency issues, and resource…