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.
npx agentmods add skills/crude-code/mcp-app/aries-writebacknpx skills add crude-code/mcp-app --skill aries-writebackgit clone --depth 1 https://github.com/crude-code/mcp-appWhat 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 | $0.00107 | $0.00887 |
| Opus 5 | $0.00053 | $0.00443 |
| Sonnet 5 | $0.00021 | $0.00177 |
| Haiku 4.5 | $0.00011 | $0.00089 |
Grade A, and why
aries-writeback 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARIES Writeback
What you're doing
The user has forecasts in Crude Code terms — usually the curves asserted in
this session's deal_forecast_wells run (their own independent forecast, or a
revised take on a seller's deck) — and wants them in ARIES. This skill
packages them as an import package: a zip of CSVs the target database's
engineer appends with ordinary MS Access import, under a new qualifier
so nothing existing is touched. Think of it as the reverse of
aries-to-valuation, with the same pinned conventions run backwards
(nominal-monthly → effective-annual).
This is v0 by design: no binary is created or modified. The deliverable is rows plus instructions; the human does the import on a copy of their own file. Say that plainly when handing it over.
What you need
- The curves, from this session. You asserted them (or translated them)
— you already hold
{qi, di, b}per stream, the anchor, and the wells. Do not re-derive parameters from anywhere else. - Code execution for the packaging script.
- The target database's
_aries/dir when available (from the explorer's triage): it fills each well's PROPNUM by API and guards against reusing an existing qualifier. Without it, PROPNUMs the user can't supply ship as placeholders with join-on-API instructions.
Workflow
- Write
curves.json(schema inaries_package.py's docstring): qualifier (short, NEW — e.g.CC2608), and per well:api,anchor_month,oil/gasparams exactly as committed viadeal_forecast_wells, optionalcumsandpropnum. Copy numbers verbatim — never round, never adjust. - Build the package:
(python3 aries_package.py curves.json --aries-dir _aries--aries-dirwhenever the target database was triaged this session.) Read the printed summary and notes. - Hand the zip to the user as a downloadable file, with a two-line explanation: it adds a new qualifier alongside their existing scenarios; the README inside walks their engineer through the Access append on a copy. Relay any PROPNUM-placeholder notes explicitly.
- If the session also produced a valuation, remind the user which run the exported curves came from — the package and the deal sheet should tell the same story.
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.
- 2d ago First seen · 70 lines · 107 tokens per session scan A 3ba60c7deabe
aries-writeback is a skill published in the GitHub repository crude-code/mcp-app (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 107 tokens to every session and 887 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…