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/causify-ai/helpers/git.deletenpx skills add causify-ai/helpers --skill git.deletegit clone --depth 1 https://github.com/causify-ai/helpersWhat 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 | $0.00020 | $0.00453 |
| Opus 5 | $0.00010 | $0.00227 |
| Sonnet 5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
git.delete 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.
What it actually says
-
Given a target
<src>(function, file, or directory), remove it from the repo cleanly with no dangling references or dead code -
Identify what
<src>is before proceeding
If <src> Is a Function
- Remove the function definition from its source file
- Find all callers: search the entire codebase for any call sites and remove or refactor them
- Remove orphaned helpers: recursively find functions that are now only
called by
<src>(or each other) and remove them too - Remove tests: delete all unit tests that exclusively test
<src>or its orphaned helpers - Clean up imports: remove any imports that were only needed by the deleted code
If <src> Is a File or Directory
- Remove the file/directory from the repo
- Find all references: search for any
import,from ... import,require, or path strings pointing to<src> - Remove or refactor each reference: delete the import and any code that depended on it, or replace it with an alternative if a substitute exists
- Remove related tests: delete test files that exclusively test the removed file/directory
- Update configs: check and update any config files (e.g.
pyproject.toml,setup.py,__init__.py,MANIFEST.in) that reference<src>
After Removal (all Cases)
- Run the test suite to confirm nothing is broken
- Run a final grep for the removed name to catch any remaining references
- Summarize the changes
- Do not commit any change
Ask for Help If Unsure How to Do
- If the task is not perfectly clear, you MUST not perform it, but ask for
clarifications
- When the task is complex, create a plan.md with 5 bullet points explaining what the plan is
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 · 44 lines · 20 tokens per session scan A 448edf046e09
git.delete is a skill published in the GitHub repository causify-ai/helpers (145 stars, last pushed 2d ago), licensed Apache-2.0. It adds 20 tokens to every session and 453 once invoked, about $0.0001 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 2026-08-30.
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…