Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/skills/prioritize/SKILL.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/crjfisher/ariadne/prioritize)<a href="https://agentmods.dev/skills/crjfisher/ariadne/prioritize"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/prioritize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/crjfisher/ariadne/prioritize"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/prioritize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.08538 |
| Opus 5.5 | $0.00024 | $0.03415 |
| Sonnet 5.5 | $0.00012 | $0.01708 |
| Haiku 4.5 | $0.00006 | $0.00854 |
Grade A, and why
prioritize 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 605 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prioritize
Graduate planned work into the user's backlog/. The plan skill leaves
proposed fixes as PlanTask rows in its task-DB at ~/.ariadne/plan/tasks/;
this skill is the deliberate, human-invoked step that turns the cheap plan into a
verified refactoring design and picks which of those rows become real backlog
tasks.
It does three things the plan engine deliberately does not: it
deep-investigates each change group against the real packages/core code (via
the refactor-investigator sub-agent) to produce a concrete refactoring plan, it
consolidates across those investigations (via the refactor-consolidator
sub-agent) to decide which groups are linked and must graduate as one epic, and it
graduates the selected rows into backlog/. Graduation runs through one
script:
.claude/skills/plan/scripts/export_to_backlog.ts
That script is the only writer of backlog/tasks/*.md cards in the pipeline
(graduate_group_docs.ts moves graduated comprehension docs alongside them). It is
never run on the autonomous sweep — graduation is always a human decision, which is
what this skill exists to make. The investigation is design-only: the
refactor-investigator reads packages/core but never writes it, and the
comprehension doc it stages graduates into backlog/ only for the groups the
user funds.
Two graduation destinations. Most groups graduate into backlog/ as
refactoring work (the pipeline below). A permanent-limitation group — a call
relationship fundamentally unknowable to static analysis, not a fixable Ariadne
bug, marked is_permanent_limitation by the plan engine and confirmed by the
human — does not become a backlog card at all. It becomes a classifier
registry entry: for these groups, dispatch the classifier-author agent in
place of refactor-investigator, producing a staged draft the human reviews and
applies via reconcile-registry --stage (see "Permanent-limitation groups"
below).
What the export does
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.
- 5d ago Changed 67fcfe587f55
- 17d ago First seen · 605 lines · 60 tokens per session scan A e61ca86d5795
prioritize is a skill published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 8,538 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
github-review-iteration
Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
write-architecture-docs
Write or rewrite architecture subsystem docs, ADRs, and reference material for the engineering team. Use when creating, updating, or reviewing docs under docs/architecture docs/, or when the user asks you to write documentation that describes the system's design.