Agent skill

Interlinked Simplification

by QuentinCody in QuentinCody/interlinked-cli

Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence.

MITAuto-check passedTesting & QA

Install Interlinked Simplification

skills CLI
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-simplification -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install QuentinCody/interlinked-cli interlinked-simplification --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/interlinked-simplification .claude/skills/interlinked-simplification && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
interlinked-simplification
GitHub stars
178
Token cost
~2.7k tokens
SKILL.md length
1,306 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence.

  • Works in 5 steps: Select the smallest useful scope; use… → Check coverage and evidence state before… → For a candidate removal or replacement,… → …
  • Tasks that involve Quality gates
  • SKILL.md covers Choose the scope, Metrics deletion trials, The five remedy lenses and Read the evidence literally, plus 4 more sections
  • Calls python

What it does

Interlinked Simplification is an agent skill from QuentinCody/interlinked-cli. Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence. Load this for simplify scan, simplify review, simplify audit, simplify status, a simplification deep-review handoff, or when interpreting simplification findings, validation, overlap, and coverage. Use interlinked-quality-gates instead for metric ratchets, automatic obligation debt, or mutation enforcement.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Testing & QA, covering Quality gates. The repository describes itself as: The harness for your harness. Local hooks, taste enforcement, and developer observability for AI coding agents (Claude Code, Codex, Cursor, Copilot CLI). The licence is MIT.

When your agent uses it

  • Tasks that involve Quality gates

Example prompts

  • “/interlinked-simplification”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Select the smallest useful scope; use review for a patch and audit for repository work.
  2. Check coverage and evidence state before reading the ranked findings.
  3. For a candidate removal or replacement, inspect runtime registration, public API,
  4. Make a source change only when the user's task authorizes it, then validate that patch with
  5. Record or reconcile the result explicitly; never infer validation from a clean static scan.

What it can do on your machine

Read from SKILL.md and the folder at commit 31b5259. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Interlinked Simplification loads about 2.7k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 1,306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from QuentinCody/interlinked-cli at commit 31b5259, republished under its MIT licence (© QuentinCody). 1,306 words, ~2,729 tokens.

Download SKILL.mdSave it as .claude/skills/interlinked-simplification/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
interlinked-simplification
description
Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence. Load this for `simplify scan`, `simplify review`, `simplify audit`, `simplify status`, a simplification deep-review handoff, or when interpreting simplification findings, validation, overlap, and coverage. Use interlinked-quality-gates instead for metric ratchets, automatic obligation debt, or mutation enforcement.

interlinked-simplification — evidence before removal

Interlinked's simplification surface finds code that may be unnecessary without treating static signals as permission to delete it. Local analysis is deterministic, offline, advisory, and does not invoke an LLM or apply a fix. The only optional write, --record, stores findings metadata; it never edits source or changes the branch.

Choose the scope

For dense JS/TS, interlinked metrics expressions <path> --json supplies advisory locations and measurements. A smaller function or lower branch count is not a complete review. Name domain concepts while preserving the context their decisions require; explicit iteration and compact named pipelines can both be appropriate. Review whether dependent checks reuse the same prerequisite observation, distinguish failure from not-evaluated, and make success claims only about what was established. Preserve command origin, suite and execution phase until availability decisions are complete. Validate relevant failure cases from the requirement; these questions are semantic review guidance, not static proofs or new automatic blockers. See interlinked-quality-gates for budgets.

CommandScope and effect
interlinked simplify scan [--cwd <path>] [--json] [--record]Run the deterministic repository scan.
interlinked simplify review [--changed|--staged|--range <base..head>] [--deep-handoff] [--json] [--record]Emit findings for one git-selected path set while retaining whole-repo context. --changed is the default; the three selectors are mutually exclusive.
interlinked simplify audit [--deep-handoff] [--json] [--record]Run the deterministic repository audit. --deep-handoff embeds a portable Agent CI request but does not submit it.
interlinked simplify status [--cwd <path>] [--json]Read locally recorded run receipts and their materialized common-corpus findings. No network.

simplify audit is intentionally distinct from top-level interlinked audit verify, which checks the tamper-evident guard-decision chain. It is also distinct from interlinked debt, whose list, show, and resolve verbs operate the automatic obligation ledger.

For a small active change, interlinked tests review [paths...] --base HEAD --json combines behavioral review prompts with at most five local simplification candidates. It does not run tests or certify the change. Python advice covers trailing continue, elif after an unconditional return/raise, large parameter-forwarding sets, and private single-use forwarding helpers. Locations identify the statement rather than charging its enclosing block. Dataclass counts, boundary validation, tuple returns and section banners are not blanket penalties. The python_simplification family and single_use_trivial_helper are advisory. Review the callers and domain contract before applying advice; retain useful abstraction boundaries.

Metrics deletion trials

For explained verbosity and erosion, metrics diagnostics --profile js-ts|python [--json] provides separate, versioned line-overlap and complexity-contribution profiles. Neither is a benchmark-compatible score or removal proof. simplify review --diagnostics js-ts|python explicitly adds its clone/pattern candidates to the normal scoped review, overlap groups, coverage receipts and optional --record flow. It runs a full census for clone context, then selects changed/staged/range candidates and related peers. Omitting the option adds no census. Source hashes remain in evidence; estimated removals are null, validation is not_run, and auto-fix is false. Python's declared analyzed paths cover only its limited diagnostic adapter, not all simplification capabilities. Retain public seams and useful domain abstractions. Use interlinked-quality-gates for profiles, budgets, gaps and snapshot comparison.

The separate metrics deletions [--cwd <path>] [--json] command joins static redundancy candidates with current coverage and exact-site mutation receipts. Public APIs, dynamic consumers and missing measurements remain review blockers. A surviving mutant, including paired forced-true/forced-false survivors, is not proof that source can be removed.

metrics deletions validate plan.json [--timeout <ms>] [--json] tests an explicit removal plan in a disposable copy. Schema 1 edits specify relative paths, exact sourceSha256, and UTF-16 half-open start/end ranges. Checks specify kind and argv; both test and typecheck are required, with optional build. Baseline checks must pass before candidate checks. A checks-passed verdict records only the supplied checks' scope, keeps review required and leaves the source checkout unchanged. Use interlinked-quality-gates for the associated receipt freshness, operator-policy and scoring contracts.

The five remedy lenses

RemedyQuestion
deleteIs this code unused, duplicated, superseded, or behaviorally inert?
stdlibCan a language standard-library facility replace the custom implementation?
nativeCan an existing framework, platform, or already-approved dependency replace it?
yagniIs the abstraction, option, factory, or seam speculative rather than currently needed?
shrinkCan the same supported behavior be expressed with less code or branching?

The current local adapters cover JavaScript/TypeScript dead-code and mutation-disposition evidence, the single-implementation-interface signal, private delegate-only wrappers, private one-product factories, never-read configuration fields, root runtime dependencies without a covered static import, and cyclomatic hotspots. They emit advisory delete, yagni, and shrink candidates. stdlib and native replacement—and semantic safety for every remedy—still require deeper review; a handoff requests all five without pretending the local scanner checked them.

Show full SKILL.md (565 more words)Show less

Read the evidence literally

StateWhat it supports
candidateA lead worth review; no safety claim.
heuristicA repeatable static signal that may still have runtime, framework, public-API, or test-seam consumers.
provenA deterministic fact in the stated scope; not proof that a deletion preserves behavior.
sandbox-validatedA candidate patch passed independently recorded checks in an isolated executor.

Every finding is advisory and auto_fix:false. Inspect its exact location, evidence, confidence, replacement, repository identity, and validation receipt. Local runs set validated impact to null because they do not create a patch or run typecheck, tests, security checks, or mutation. --record persists the same evidence; it does not promote its state.

Estimated line/dependency deltas are prioritization hints. overlap_group is non-null only for a connected component of intersecting known source spans or a shared dependency-removal claim; same-file non-overlapping candidates stay independent. Never sum members of one group. Prefer independently validated impact when it exists.

Coverage is part of the result

Read coverage.status, selected/analyzed file counts, per-language/source status, exclusions, missing paths, and limitations before making a repository-wide claim. Each source's analyzed_paths is the exact sorted repository-relative read set; the top-level analyzed count is their in-scope union, not a supported-extension count. Default local detectors support JS/TS; the explicit Python diagnostic adapter contributes its own measured paths and limited scope. runtime loading, reflection, framework wiring, and public surfaces can escape static reachability.

An empty report means “No findings in covered scope.” It does not mean the repository is globally lean. partial or unavailable coverage must remain visible in summaries and handoffs.

Recording and reconciliation

Without --record, a report is ephemeral. With it, Interlinked appends a local run receipt to .interlinked/findings/simplification-runs.jsonl and upserts each finding into the existing .interlinked/findings/corpus.jsonl under extensions.simplification. Corpus IDs bind a stable repository ID plus finding fingerprint, not the absolute checkout path. This is not a parallel database, but generic findings/reconciliation commands still filter legacy review rows; simplify status and impact are the current simplification-aware projections. --record --json keeps stdout as the canonical simplification report.

Use simplify status to inspect recorded coverage and materialized findings. Recording is an explicit user action: a scanner must not create a debt receipt or finding merely because a candidate was deferred.

Safe review workflow

  1. Select the smallest useful scope; use review for a patch and audit for repository work.
  2. Check coverage and evidence state before reading the ranked findings.
  3. For a candidate removal or replacement, inspect runtime registration, public API, compatibility, security/trust boundaries, data-loss behavior, accessibility, and tests.
  4. Make a source change only when the user's task authorizes it, then validate that patch with the project's typecheck/tests and any relevant security or mutation checks.
  5. Record or reconcile the result explicitly; never infer validation from a clean static scan.

For deeper semantic work, emit interlinked simplify review --deep-handoff --json or interlinked simplify audit --deep-handoff --json. A deep handoff requires readable non-null Git commit and tree identities; ordinary local reports may retain nullable Git provenance. The artifact is scope-bound, carries deterministic finding fingerprints, and says submission.status: not_submitted. It is schema-portable but not submission-ready: internal source-only Agent CI builders add workspace, inventory, exact-version capability, P4 v2 partition, and request-bound P5 validation bindings. No Cloud job, Workflow, model, or Sandbox runs here.

  • interlinked-quality-gates — metric water-lines, dead-code categorization, mutation evidence, automatic obligations, and manual debt-marker syntax.
  • interlinked-spec-audit — prose-spec drift and the legacy review-finding reconciliation tools.
  • interlinked-observability — evidence-classed interlinked impact reporting.

© QuentinCody, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/interlinked-simplification of QuentinCody/interlinked-cli.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 31b5259

Compare with similar skills

Interlinked Simplification next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Interlinked Simplification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interlinked Simplification this skillQuentinCody/interlinked-cli178—~2.7kAutomated safety check: PassMIT
Feature Plannerserendipity1004/cc-feature-implementer176—~2.4kAutomated safety check: PassNone
Ccg Workflowfengshao1227/ccg-workflow5.9k—~2.3kAutomated safety check: PassMIT
Conducty Checkpointrobertbarclayy/conducty176—~1.5kAutomated safety check: PassMIT
Mission Plannerjdforsythe/forge151—~3.5kAutomated safety check: PassMIT
Quality Gate0xNyk/lacp305—~382Automated safety check: PassMIT

Similar skills

  • Feature Planner

    serendipity1004/cc-feature-implementer

    Creates phase-based feature plans with quality gates and incremental delivery structure.

    176 GitHub stars~2.4k tokensUpdated 9 mo ago
    Testing & QAAuto-check passed
  • Ccg Workflow

    fengshao1227/ccg-workflow

    How to run a non-trivial change end to end with the CCG role tools (ccganalyze / ccgdesign / ccgbuild / ccgdebug / ccgoptimize / ccgreview / ccgtest) and the verify- quality gates.

    5.9k GitHub stars~2.3k tokensUpdated 22 days ago
    Testing & QAAuto-check passed
  • Conducty Checkpoint

    robertbarclayy/conducty

    Quality gate between parallelization groups. An agent skill from robertbarclayy/conducty.

    176 GitHub stars~1.5k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed
  • Mission Planner

    jdforsythe/forge

    Decomposes goals into team blueprints using evidence-based scaling laws, topology selection, and role design.

    151 GitHub stars~3.5k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed
  • Quality Gate

    0xNyk/lacp

    Production quality gate for agent sessions. An agent skill from 0xNyk/lacp.

    305 GitHub stars~382 tokensUpdated 15 days ago
    Testing & QAAuto-check passed
  • Deploy Workflow

    nwiizo/ccswarm

    Release deployment process for ccswarm. An agent skill from nwiizo/ccswarm.

    153 GitHub stars~582 tokensUpdated 23 days ago
    Testing & QAAuto-check passed

More from QuentinCody/interlinked-cli

All 12 skills in this repo
  • Interlinked Cowork

    QuentinCody/interlinked-cli

    Package, test, and operate the experimental Interlinked Cowork plugin.

    178 GitHub stars~1.6k tokensUpdated 5 days ago
    Auto-check passed
  • Interlinked

    QuentinCody/interlinked-cli

    Overview and router for the Interlinked CLI — a local guard, quality-enforcement, simplification-review, semantic-code-search, and observability layer for AI coding agents.

    178 GitHub stars~4.1k tokensUpdated 5 days ago
    Auto-check passed
  • Interlinked Coordination

    QuentinCody/interlinked-cli

    Coordinate with other agents/humans via the optional Interlinked MCP Server, and use local checkpoints & file reservations.

    178 GitHub stars~2.9k tokensUpdated 5 days ago
    Auto-check passed
  • Interlinked Observability

    QuentinCody/interlinked-cli

    Investigate agent activity and JSONL/gzip evidence. An agent skill from QuentinCody/interlinked-cli.

    178 GitHub stars~10k tokensUpdated 5 days ago
    Auto-check passed
  • Interlinked Semantic Index

    QuentinCody/interlinked-cli

    Install and operate Interlinked's optional local semantic function index.

    178 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed
  • Interlinked Spec Audit

    QuentinCody/interlinked-cli

    Keep prose specs and design docs honest against the code using Interlinked's spec-audit system.

    178 GitHub stars~3.3k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Interlinked Simplification

What does Interlinked Simplification do?

Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence. Interlinked Simplification is an agent skill from QuentinCody/interlinked-cli. Find, review, record, and audit opportunities to delete, replace, defer, or shrink code with Interlinked's advisory simplification evidence.

When should I use Interlinked Simplification?

Interlinked Simplification fits situations like: tasks that involve Quality gates.

How do I install Interlinked Simplification in Claude Code?

Run `npx skills add QuentinCody/interlinked-cli --skill interlinked-simplification -a claude-code`. Or copy the skill folder (skills/interlinked-simplification in QuentinCody/interlinked-cli) into .claude/skills/interlinked-simplification in your project. Claude Code loads it when a task matches its description.

How do I install Interlinked Simplification in Codex?

Run `npx skills add QuentinCody/interlinked-cli --skill interlinked-simplification -a codex`. Or copy the skill folder (skills/interlinked-simplification in QuentinCody/interlinked-cli) into .agents/skills/interlinked-simplification in your project. Codex loads it when a task matches its description.

Can I use Interlinked Simplification in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QuentinCody/interlinked-cli --skill interlinked-simplification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interlinked-simplification, .gemini/skills/interlinked-simplification, .github/skills/interlinked-simplification and .opencode/skills/interlinked-simplification in your project.

What does Interlinked Simplification need to run?

Going by SKILL.md and its folder, Interlinked Simplification needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Interlinked Simplification access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Interlinked Simplification safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Interlinked Simplification use?

Interlinked Simplification is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Interlinked Simplification use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Interlinked Simplification?

Skills that share tags, products or a category with Interlinked Simplification: Feature Planner (serendipity1004/cc-feature-implementer, 176 stars), Ccg Workflow (fengshao1227/ccg-workflow, 5.9k stars), Conducty Checkpoint (robertbarclayy/conducty, 176 stars) and Mission Planner (jdforsythe/forge, 151 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interlinked Simplification?

QuentinCody (a GitHub user) maintains it in QuentinCody/interlinked-cli, which has 178 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 2, 2026.

Source: QuentinCody/interlinked-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.