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 Abilityai/abilities --skill implementgit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/implement)<a href="https://agentmods.dev/skills/abilityai/abilities/implement"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/implement/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/abilityai/abilities/implement"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/implement.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 | $0.00027 | $0.01164 |
| Opus 5.5 | $0.00011 | $0.00466 |
| Sonnet 5.5 | $0.00005 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
implement 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 1mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Feature
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.implement vX.Y — recent: <summary>. Then proceed.
End-to-end feature implementation from requirements to tested, documented code.
Purpose
Autonomously implement features by:
- Parsing requirements from file, GitHub issue, or inline description
- Understanding existing patterns via feature flows
- Implementing with minimal necessary changes
- Creating and running tests
- Updating documentation
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Requirements | docs/requirements/*.md |
✅ | Feature specs | |
| GitHub Issues | GitHub repo | ✅ | Issue details | |
| Feature Flows | docs/memory/feature-flows/ |
✅ | Existing patterns | |
| Architecture | docs/memory/architecture.md |
✅ | System design | |
| Source Code | src/ |
✅ | ✅ | Implementation |
| Tests | tests/ |
✅ | ✅ | Test files |
Arguments
$ARGUMENTS:- File path:
docs/requirements/MY_FEATURE.md - Issue number:
#42or42 - Inline description:
"Add endpoint for X that does Y"
- File path:
Process
Step 1: Parse Requirements
If file path provided: Read and parse the requirements document.
If issue number provided:
gh issue view ${ARGUMENTS#\#} --json title,body,labels
If inline description: Use the provided description directly as requirements.
Extract:
- Feature name/ID
- Core requirements (what must be built)
- Acceptance criteria (how to verify it works)
- Related features/flows (what to study first)
Step 2: Study Existing Patterns
Read relevant feature flows to understand existing patterns. Based on requirements, identify 2-4 related flows and read them.
Also read:
docs/memory/architecture.md- for system contextCLAUDE.md- for development rules
Step 3: Plan Implementation
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.
- 1mo ago First seen · 170 lines · 27 tokens per session scan A 5edd1abf7b94
implement is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 1,164 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.