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 skills add tata1mg/catalyst-core --skill new-featuregit clone --depth 1 https://github.com/tata1mg/catalyst-coreWrote 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/tata1mg/catalyst-core/new-feature)<a href="https://agentmods.dev/skills/tata1mg/catalyst-core/new-feature"><img src="https://agentmods.dev/badge/skills/tata1mg/catalyst-core/new-feature/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/tata1mg/catalyst-core/new-feature"><img src="https://agentmods.dev/badge/skills/tata1mg/catalyst-core/new-feature.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 | $0.00058 | $0.01128 |
| Opus 5.5 | $0.00023 | $0.00451 |
| Sonnet 5.5 | $0.00012 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
new-feature 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 18d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New feature workflow (catalyst-core)
This repo tracks 1.0 work as an Epic → Story → Task hierarchy on GitHub (see issue #329 for the current 1.0 epic). This skill walks a contributor through the same steps used to ship task #359 (unified error codes), so the workflow doesn't have to be reinvented each time.
Go through the steps below in order, asking the user at each one rather than assuming. Do not skip a step because it seems obvious — the user may have context you don't (e.g. this might not belong under the current epic at all).
Step 1 — Locate or create the tracking issue
Ask:
- Does this already have a GitHub issue? If yes, get the number and read it.
- If no: does it belong under the current 1.0 epic (#329)? If yes, which Story?
List the open stories (
gh issue view 329 --json bodyor check the sub-issues via the GraphQLsubIssuesfield) and ask the user to pick one, or confirm it's net-new/outside the epic. - Create the issue with a clear headline + description (see the #359–#368 issues
for the format:
## Description,## Acceptance criteria,## Parent). - If it nests under a Story, link it as a native GitHub sub-issue via the
addSubIssueGraphQL mutation (see prior session history for the exact call shape) — don't just mention the parent in text. - Assign the issue to the contributor.
Step 2 — Create the branch
- Derive a
feature/<slug>(orfix/<slug>for bug fixes) name from the issue title. - Branch from
origin/main, not from whatever is currently checked out — the current branch may have unrelated in-progress/uncommitted work that shouldn't be inherited. - If the current working tree has uncommitted changes or is mid-work on another
branch, use
git worktree add ../catalyst-core-<slug> <branch>instead of switching branches in place, so the two efforts don't collide.
Step 3 — Proposal before code (gate)
Before writing any implementation:
- Post a design comment on the issue covering: what's being built, why this approach over alternatives, what files/modules it touches, and a closing section on why this matters for the current release (ties back to the epic/story it gates, or explains why it doesn't gate anything if it's independent work).
- Do not start implementation until this is posted. If the user says the change is trivial enough to skip (e.g. a one-line fix, a typo), that's a valid reason to skip — but ask first, don't assume.
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.
- 18d ago First seen · 90 lines · 58 tokens per session scan A 9e30c9131d75
new-feature is a skill published in the GitHub repository tata1mg/catalyst-core (92 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,128 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 2026-09-30.
Other skills, from other repositories
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
cuga-github-issues
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…
implement-issue
Implement a Linear brief in a named GitHub repo. Use when the brief skill is implement-issue or the user wants a new branch and draft PR.