interlinked-quality-gates

A set of rules for keeping code-quality measurements from getting worse. It covers measures such as test coverage, code complexity, and mutation testing, which checks whether tests can detect altered code.

In plain words
What is it for?
Use it when configuring or handling blocked quality checks, updating quality baselines, or meeting coverage, complexity, and mutation-testing requirements.
Why use it?
It prevents quality targets from being quietly lowered when a change is difficult to implement.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/quentincody/interlinked-cli/interlinked-quality-gates
Any agent
npx skills add QuentinCody/interlinked-cli --skill interlinked-quality-gates
Clone the repo
git clone --depth 1 https://github.com/QuentinCody/interlinked-cli

Made for: Claude Code, Codex.

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00144 $0.07588
Opus 5 $0.00072 $0.03794
Sonnet 5 $0.00029 $0.01518
Haiku 4.5 $0.00014 $0.00759

Measured 2d ago against content hash 74d3e191ae8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interlinked-quality-gates 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.

skills/interlinked-quality-gates/SKILL.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

interlinked-quality-gates — the metric ratchets

Every quality metric is a water-line stored in a JSON file under .interlinked/. The gates enforce "may only move in the tightening direction": coverage/mutation scores may only rise; caps may only fall. The harness raises water-lines itself (internal writes); an agent hand-lowering a water-line is the canonical gate-gaming move and is blocked. North star: ~100% coverage paired with mutation testing.

When a gate blocks you, the correct move is always to meet the bar — decompose, add a test, cover the line — never to loosen the baseline. The strict gates (cyclomatic, per-edit coverage) have no suppression and no env bypass; decomposition or a test is the only way past. The habit that pays here is decompose-first: extract helpers as you write branchy functions, rather than waiting for the gate to block. (Measured on the harness's own repo across 17+ sessions of the strongest available models, at an identical per-edit rate — so it is a property of how models write branchy code, not of one codebase.)

The gates you bump into at edit time

These run before an edit lands. The local metric ratchets use delta semantics: holding or reducing existing debt is allowed. Per-edit mutation is separately configurable as off, warn, or block.

Gate Blocks when Threshold Correct response
Line cap a Write/Edit grows a cappable file past its ceiling 500 lines (DEFAULT_MAX_LINES) Decompose into a re-exporting entry + sibling modules
Cyclomatic — over cap edit adds/raises a function over the hard cap 22 Extract cohesive branches into named helpers
Cyclomatic — slew a uniquely-named ≤cap function jumps >2 branches in one edit tolerance 2/edit Extract cohesive branches into named helpers; do not stage one logical complexity increase across edits
Cognitive — over cap edit leaves a function over the cognitive cap 30 Flatten: guard clauses, extract the deepest-nested block
Cognitive — slew a uniquely-named ≤cap function jumps >4 cognitive points in one edit tolerance 4/edit Flatten rather than extract-in-place; a branch pulled out unchanged keeps its nesting cost
Per-edit coverage edit adds an uncovered executable line/function, or drops a file's coverage vs its high-water gate default on; drop ε 0.005; hard floor min_coverage default 0 (off) Stay within the source/test pair and add coverage; default debt mode allows the first uncovered/red edit but blocks unrelated wandering

Read the full file on GitHub · 468 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 468 lines · 144 tokens per session scan A 74d3e191ae8b

Subscribe to this mod's changes

interlinked-quality-gates is a skill published in the GitHub repository QuentinCody/interlinked-cli (13 stars, last pushed 15d ago), licensed MIT. It adds 144 tokens to every session and 7,588 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

agent-integration

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…

entireio/cli · 89 tokens

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

code-assist

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

mikeyobrien/ralph-orchestrator · 53 tokens

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

css-design-tdd

Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.

xiaolai/vmark · 49 tokens

mobiai-mobile-tdd

You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.

ArisGuimera/MobiAI-Core · 38 tokens