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 add-pipeline-stagegit 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/add-pipeline-stage)<a href="https://agentmods.dev/skills/abilityai/abilities/add-pipeline-stage"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/add-pipeline-stage.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01669 |
| Opus 5 | $0.00023 | $0.00834 |
| Sonnet 5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade B, and why
add-pipeline-stage scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Show available skills from `ls .claude/skills/` as a hint. How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Pipeline Stage
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.add-pipeline-stage vX.Y — recent: <summary>. Then proceed.
Extend an existing pipeline with a new stage. Edits projects/<slug>/pipeline.yaml non-destructively and revalidates.
Use this instead of editing pipeline.yaml by hand when you want guardrails on retry/timeout defaults, DAG acyclicity, and skill-existence checks.
Process
Step 1: Resolve pipeline
Expect <pipeline-slug> as the first positional argument. If missing, list projects/*/pipeline.yaml and ask which one.
Validate that projects/<slug>/pipeline.yaml exists. If not, suggest /add-pipeline to create it.
Step 2: Read current pipeline
PIPELINE_FILE="projects/$SLUG/pipeline.yaml"
yq '.stages[].id' "$PIPELINE_FILE" # existing stage IDs
Show the user the current stage list (compact: id (skill) → next).
Step 3: Ask stage parameters
Q1 — Stage id
- Free text. Validate:
^[a-z][a-z0-9-]{0,40}$. Refuse if it collides with an existing stage id (suggest a different id). - If passed as second positional arg, skip this question.
Q2 — Skill to invoke
- Free text. Validate:
[ -d .claude/skills/<skill-name> ]. If the skill doesn't exist, warn but allow (user may scaffold it after). - Show available skills from
ls .claude/skills/as a hint. - If the stage is another fleet agent's playbook, ask for the agent name and write
agent: <name>on the stage (skip the local-directory check; the tick calls it as a one-line playbook call —protocols/playbook-call.md).
Q3 — Position in DAG
Use AskUserQuestion with options:
Append at end(runs after the current last stage) — most commonAfter a specific stage(free-text picker among existing stage ids)Parallel to a stage(samedepends_onas the picked stage — fan-out)Terminal — no successor(runs on cycle but nodepends_onpoints to a successor; useful for measurement/audit stages)
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.
- 8d ago First seen · 169 lines · 46 tokens per session scan B 2d66ec2f0e97
add-pipeline-stage is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,669 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.