niksavis
UserA harness that ships a development process to coding agents and enforces it. One YAML catalog projects instructions, skills, subagents and permissions to Claude, Codex and Copilot. Git hooks refuse bad work at commit time. A loop drives each unit of work to a merge in an isolated worktree, with phase derived from a tracked work graph.
Categories
Indexed Skills (41)
python-guidelines
Make the design calls no linter can check — where an oversized file splits, whether a name or docstring carries meaning, whether an abstraction earns its keep, when a suppression is legitimate, and how to satisfy a size or complexity ratchet without gaming it. Use when a size or complexity gate has just failed, before adding a noqa or nosec, when deciding what to raise and what to catch, or when shared state is reached from more than one concurrent lane.
catalog-authoring
Author and improve basicly catalog sources — skills and fragments — in their YAML source format (never a discoverable .md), then project and verify them. Use when adding or editing a skill or fragment, building a catalog, or deciding where guidance should live (always-on fragment vs on-demand skill).
conventional-commits
Construct a valid Conventional Commits message for this repo before running `git commit`, covering type/scope, the "!" breaking-change marker, description rules, and the required trailing tracker record id. Use whenever writing or reviewing a commit message, or when a commit is rejected by the commit-msg/tracker-commit-msg hooks.
harness-loop
Drive a unit of work through the basicly harness loop end-to-end (intake → classify → decompose → build → verify → validate → ship → done) with `basicly loop` over the owned tracker ledger, agent-agnostic across Claude/Codex/Copilot. Teardown is folded into the ship advance and the retro is a tracker comment; neither is a phase. Use when starting or resuming non-trivial development in a harness-enabled repo, when deciding what phase a tracked issue is in, or when coordinating the checkpoints, gates, and bounded rework the loop enforces.
session-finish
Close out a working session with a usage-statistics report, a self-improvement retro, and a pickup-clean handoff summary. Use when the user says the session is done ("wrap up", "finish the session", "close out"), before ending a long autonomous run, or whenever a summary of what changed and what the agent actually used is wanted.
tool-br
Use br (beads_rust) as the primary task/issue tracker for this repo. Trigger when planning work, creating or claiming issues, checking what is ready to work on, or preparing a commit that must reference a beads issue id.
tool-git
Use git for repository state inspection, safe staging, diff review, and history-aware change management. Trigger when the task involves commits, branches, diffs, or version control decisions.
worktree-isolation
Isolate non-trivial work in a sibling git worktree using `basicly worktree`, covering sibling placement on a harness branch, dependency + git-hook provisioning, and safe cleanup. Use when starting a unit of work that should not touch the main checkout, when parallel tracks would collide, or when deciding whether a change needs its own worktree.
release-process
Cut a release of this repository with `basicly release`, then do the three steps that command deliberately leaves to a human - deciding the version, pushing, and replacing the release page with the highlights. Use when asked to cut a release, tag a version, prepare release notes, or check whether a release published.
python
Write and edit Python for this repo — type hints pathlib and cross-platform subprocess and shell-out. Use when creating or changing .py files wiring up a subprocess call chasing a test that passes on POSIX but fails only on Windows CI (a WinError 2 or a mangled backslash path) or second-guessing syntax that looks wrong for an older Python (an unparenthesized multi-exception except clause).
test-discipline
Write isolated order-independent automated tests that assert on observable behavior rather than private internals. Use when writing reviewing or debugging any test (unit integration or end-to-end) in any language especially when tests share fixtures touch global or filesystem state flake depending on run order or reach into implementation details.
harness-client
Attach to a running basicly supervisor as a second session — observe live status, present its pending decisions to a human conversationally, and record the answers. Use when a supervisor is already running (or may be) and you are not the one driving it, to check what the factory is doing, unblock a lane that waits on a judgment, or answer a queued decision.
decompose-plan
Cut a unit of work into children the plan gate will accept — testable acceptance criteria in EARS, disjoint or declared scope globs, an acyclic dependency graph, a token budget, an integrity level, and the command that demonstrates each child end to end. Use at DECOMPOSE, when a plan gate has just refused a child, or when a child turns out to have no consumer-visible behaviour to check.
falsify-first
Attempt to break a claim - an invariant, a design premise, a measurement - with a concrete counterexample search before defending or adopting it, and read each kill for the precondition that carried the weight. Use before an invariant enters a plan, a design note or a gate, before a measured number becomes a claim, and whenever a candidate rule survived only because nobody attacked it.
interface-facts
Establish a fact about an external interface - a CLI flag, an API field, a model id, a price, a limit, a version - by fetching the vendor's current documentation instead of recalling it. Use before writing code, a design note, or any claim that depends on how a third-party tool behaves, and whenever a repo document already asserts such a behaviour.
repair-in-place
Fix a named defect in the lane's own worktree, briefed with the actual findings and without re-planning or widening scope. Use at REPAIR after verify or validate failed, when a landing bounced, or whenever the temptation is to re-read the requirement and start again.
root-cause
Establish why something actually happened by iterating why until the answer stops changing, with each link citing an observation - and know the two ways the method lies. Use before filing a bead off a failure, before proposing a rule or a gate to prevent a recurrence, when a fix addresses a symptom, or when a retro asks for a cause.
tier-injection
Install the portable tier injection kit so a subagent spawns on the model its declared tier resolves to, instead of the host default. Use when setting up tier injection in this or another repository, when a subagent ignores the tier its definition declares, or when deciding whether a host can pin a spawn's model at all.
validate-as-consumer
Exercise a verified change the way a consumer would — in the operational environment, against the requirement that asked for it — instead of re-running the gate suite that already passed. Use at VALIDATE, before claiming a capability on a README or release note, or whenever "the tests pass" is standing in for "the feature works".
work-tracker
Use the owned work tracker - the append-only event ledger under .basicly/ledger/ - as the primary task/issue tracker for this repo, reading it through the kit CLI and writing it through the engine seam, and know what it refuses. Trigger when planning work, creating or claiming an issue, checking what is ready to work on, counting or querying issues in bulk, or preparing a commit that must reference a tracker issue id.
tool-ast-grep
Use ast-grep for structural code search and rewrite based on syntax trees. Trigger when text search is too imprecise for code-aware matching.
tool-curl
Use curl for low-level HTTP requests, headers, and data transfer debugging. Trigger when APIs, webhooks, download checks, or protocol-level diagnostics are required.
tool-fd
Use fd or fd-find for fast filename and path discovery with sane defaults. Trigger when file enumeration by pattern is needed without complex find syntax.
tool-jq
Use jq to parse, filter, and transform JSON in shell pipelines. Trigger when structured JSON extraction or reshaping is needed.
tool-ripgrep
Use ripgrep for extremely fast text and regex search across repositories. Trigger when locating symbols, strings, or patterns at scale.
tool-sd
Use sd for fast, readable search-and-replace in files with safer defaults than sed. Trigger when batch textual replacements are needed across files.
tool-shellcheck
Use shellcheck to statically analyze shell scripts for bugs, portability issues, and quoting mistakes. Trigger whenever shell scripts are created or modified.
tool-starship
Use Starship for prompt configuration, module tuning, and cross-shell prompt consistency. Trigger when prompt rendering, startup latency, or shell prompt content needs changes.
tool-tmux
Use tmux for session orchestration, pane/window control, and resilient long-running terminal workflows. Trigger when the task needs terminal multiplexing or keybinding troubleshooting.
tool-tree
Use tree to visualize directory layout quickly in a token-efficient form. Trigger when understanding project structure or summarizing file hierarchies.
tool-typos
Use typos to detect spelling mistakes in code, comments, and docs with low false positives. Trigger when proofreading source content or enforcing text quality.
tool-uv
Use uv for fast Python dependency sync, environment management, and command execution. Trigger for Python setup, install, lint, test, and script workflows in this repo.
tool-wezterm
Use WezTerm for terminal emulator configuration, keybindings, and cross-platform shell launch behavior. Trigger when terminal UI shortcuts or startup profiles need adjustment.
tool-wget
Use wget for robust non-interactive downloads, retries, and mirror-style fetch operations. Trigger when reliable file retrieval or resumable downloads are needed.
tool-xh
User-invoked skill tool-xh. A human runs it by name.
tool-yq
User-invoked skill tool-yq. A human runs it by name.
tool-zsh
Use zsh for shell startup, profile troubleshooting, and non-interactive command validation. Trigger when the task touches shell behavior, aliases, completions, or prompt startup.
node
Use Node and npm in this repo for the markdownlint git hook and other node tooling. Use when running npm or npx committing or pushing from a script or background job on WSL or debugging a node-based hook that resolves the wrong node binary.
tool-bat
- Preview file contents with line numbers and syntax highlighting. - Show focused line ranges during debugging and review. - Improve readability of piped terminal output.
tool-fzf
- Add interactive selection to shell workflows. - Narrow large candidate lists quickly with fuzzy matching. - Run non-interactive fuzzy filtering in scripted pipelines.
tool-git-delta
- Improve readability of git patch review in terminal. - Present staged and unstaged diffs with syntax awareness. - Configure git pager output for ongoing review workflows.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.