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/plearaj/code-flow-skill/code-flow-qualitynpx skills add plearaj/code-flow-skill --skill code-flow-qualitygit clone --depth 1 https://github.com/plearaj/code-flow-skillWhat 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 | $0.00049 | $0.10094 |
| Opus 5 | $0.00024 | $0.05047 |
| Sonnet 5 | $0.00010 | $0.02019 |
| Haiku 4.5 | $0.00005 | $0.01009 |
Grade A, and why
code-flow-quality 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 yesterday.
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 — 704 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Flow — Quality Report
Read the map this project has already written under Code_Flows/ and report where
it shows duplicated intent, needless complexity, code that nothing reaches,
responsibilities and dependencies that sit wrong, and modules whose interface
costs a caller more than the implementation behind it hides.
This skill never edits source code. code-flow-map adds missing docstrings
as it traces; this one writes documents and stops. Consolidating duplicates and
deleting suspected-dead code carry real blast radius, and that call is the user's.
User Input
The user's request carries two optional flags, --read-code and --rules. Step 1
reads them.
Instructions
Follow these steps exactly.
1. Read the Arguments
The user's request carries two optional flags:
--read-code— after deriving candidate findings from the map, open the files those candidates cite and confirm each against current source. Off by default. It requires the source tree to be present and current, not merely the artifacts underCode_Flows/. It also decides two of step 3's detectors outright: open-closed and liskov-substitution cannot be settled from the map and do not run without it.--rules [source ...]— also check the map against rules this project has already written down. Off by default. A source is a path to a document, the wordauto, or a rule written inline in quotes; several may be given, separated by spaces or commas, and--ruleswith no value meansauto. Step 2 loads them and step 3's last detector checks them. This is how a project's own standard — aCLAUDE.md, anAGENTS.md, a Spec Kit constitution, a team style guide — gets reported with the same evidence and the same honesty as DRY, KISS and YAGNI, instead of being a thing everyone agreed to and nobody checks.
There is no feature name to parse: this command analyzes the whole map. If the input contains anything else, say what you read, ignore it, and carry on — do not treat it as a filter, a path, or a flow name.
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.
- yesterday First seen · 704 lines · 49 tokens per session scan A 77677aca466d
code-flow-quality is a skill published in the GitHub repository plearaj/code-flow-skill (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 49 tokens to every session and 10,094 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…