ash-skills
01Plugin Claude Code
Plugin marketplace listing 1 plugin: ash.
Plugin Claude Code
Plugin marketplace listing 1 plugin: ash.
Plugin Claude Code
ASH engineering skills: 43 guardrail skills in a four-layer architecture (hooks, norms, hubs, leaves), distilled from cross-repo lessons learned and committee-ratified. Includes the Layer 0 hooks (push gate, skill fire log, destructive-SQL warn, session recon, schedule-cost warn) and the always-on norms injected at…
Skill Claude CodeCodex
Apply input minimisation, output discipline, and a human-in-the-loop gate to every surface that sends data to an LLM. Triggers when building or editing any send-to-LLM path: an Edge Function calling a model, a draft-commentary or summary generator, an auto-resolver, a cash-allocation suggestion, a classification call…
Skill Claude CodeCodex
The unit of change is the action or the fact, never the named list of places someone handed you. Before shipping a gate, constraint, rename, drop, or a correction to any duplicated, mirrored, or denormalised value, grep the whole repo — app, tests, seeds, scripts, open branches, and the built or rendered output — and…
Skill Claude CodeCodex
Keep a live, committed checkpoint log during any work unit expected to span multiple commits or sessions. Each commit ships with a short note in the log, what the commit did, the key decision and why, any deviation from plan; closing the unit requires an explicit walk of the checklist including the wiring steps.…
Skill Claude CodeCodex
Before spawning a fleet of agents, publish a roster for the operator's approval - role, model tier, token budget, scope and single artifact per agent - and brief each agent with pre-verified facts instead of questions. Triggers when appointing a lead agent, delegating a multi-agent wave, planning a commission whose…
Skill Claude CodeCodex
Run a three-lens committee review of a whole project or major subsystem: positive, adversarial, and neutral-chair reviewers over one shared evidence base, with attribution-stripped consolidation and item-by-item voting. Use when the user asks for a committee review, a multi-perspective audit, a "three Fable review"…
Skill Claude CodeCodex
Always ask explicitly before pushing to a remote or fast-forwarding a protected branch. Per-action authorisation, not standing approval. Triggers on any git push, merge, or branch fast-forward operation, regardless of whether previous pushes in the same session were approved.
Skill Claude CodeCodex
Compare bearer tokens, API secrets, signatures, and password-equivalents with a constant-time comparison (hash both sides, then crypto.timingSafeEqual) — never == or short-circuiting string equality. Triggers when writing any code that checks a secret against a stored or expected value. Does not fire on comparing…
Skill Claude CodeCodex
Adversarially review a specific change, design, or finding by having Claude debate one or more INDEPENDENT AI agents (e.g. Gemini or GPT in Antigravity, several models at once) over a shared file relay, with mandatory file:line citations, live read-only evidence, and a converge-or-two-positions outcome. Use when the…
Skill Claude CodeCodex
In a UTC server or serverless runtime, new Date("YYYY-MM-DD") is UTC midnight and renders as the previous day in western timezones. Parse date-only strings into explicit local components (new Date(y, m-1, d)) anywhere a date becomes a display string or a day-of-week. Triggers when parsing a date-only string…
Skill Claude CodeCodex
Every database migration plan ships with a post-apply verification query that reads catalog state directly, separate from any runtime tests. Triggers on any work involving a database migration, schema change, RLS policy change, trigger change, or constraint change.
Skill Claude CodeCodex
Three gates for AI-rewritten claims, owner-only facts, and machine-parsed output in any generated document. Claims: diff an AI rewrite claim by claim against the source — the original wins unless the owner confirms. Gaps: facts the generator does not hold render as loud allowlisted placeholder tokens, never plausible…
Skill Claude CodeCodex
When a dependency major-bump could silently change on-disk formats or behaviour and runtime data cannot distinguish success from failure, answer the question from the dependency's own source: npm pack both versions and diff the file that decides the behaviour, offline, before hunting for a device repro. Triggers on…
Skill Claude CodeCodex
Nothing enters a file without a present need. Code earns its place by a caller that exists, a comment by saying what the code cannot, flexibility by a stated requirement. Triggers on over-engineered, over-commented, YAGNI, speculative, gold-plating, "just in case", "future-proofing", "flexibility", and on "simplify" /…
Skill Claude CodeCodex
A 2xx from a transactional email API means accepted, not delivered. Verify actual delivery in the provider's dashboard or webhooks, check the account-level suppression list, verify every recipient leg of a multi-recipient flow, and confirm a mailbox exists before pointing a send at it. Triggers when adding or changing…
Skill Claude CodeCodex
A rule asserted only in prose — "single source of truth", "never auto-X", "these must match" — is a comment, not a control; if a violation can exist without failing the build, one eventually will and it will look official. Triggers when writing or encountering any comment, doc, or convention that asserts an invariant…
Skill Claude CodeCodex
An environment variable change is not live until the artifact that reads it is rebuilt, redeployed, or re-reads it — and a wrong-but-present value fails silently. Know for each variable whether it is baked at build time or read at request time. Triggers when adding or editing any env var, CI secret, or hosted config…
Skill Claude CodeCodex
A subagent, reviewer, or scout report is evidence, not findings — and so is your own first-hand defect analysis. Re-derive every Critical or High claim, everything touching a regulatory anchor, and the reasoning about the fix from the primary source before acting or writing it into a durable artifact. Triggers when…
Skill Claude CodeCodex
When proposing anything as deferred, out of scope, or "for a later phase", plant a grep-able flag at the place where the deferred work will land. Triggers whenever the words "deferred", "out of scope", "later commit", "later phase", "future work", or similar appear in plans, commits, or design discussions.
Skill Claude CodeCodex
When creating or reviewing any endpoint or control that touches money or shared state, two rules apply together. Every endpoint that spends money (LLM, email, SMS, payment) or writes shared state (bookings, slots) gets a per-IP volume cap the day it is created — anyone can POST directly, bypassing the UI. And any…
Skill Claude CodeCodex
Produce a structured handover note when the context window fills or the user asks to wrap up. Run /context first to read the real percentage; never estimate — and where the harness cannot invoke /context, record the gap verbatim rather than inventing a figure. Triggers when the context band reaches amber or red, when…
Skill Claude CodeCodex
Playbook for the always-on norm "one message per failure mode; error level is for terminal states only". Load when writing a catch block, a user-facing error string, a disabled control, a progress indicator, or choosing telemetry levels. Does not fire on content loss through filters (no-silent-data-drop) or on test…
Hook
Runs when a session starts, executing norms-inject.mjs and session-recon.mjs via node (2 commands). From randommonicle/claude-skills.