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 agents/argos-ci/docs/agent-skillsgit clone --depth 1 https://github.com/argos-ci/docsWhat 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 | $0.00032 | $0.00494 |
| Opus 5 | $0.00016 | $0.00247 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
agent-skills 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills
Argos publishes agent skills — reusable instruction packs your AI assistant loads to perform Argos tasks reliably, without you writing long prompts. They work with assistants that support skills, such as Claude Code, Codex, and Cursor.
Available skills
| Skill | What it teaches the agent |
|---|---|
argos-cli |
The Argos CLI: commands, flags, authentication rules, and output formats. |
argos-pr-review |
A complete pull-request visual review workflow: find the Argos build, inspect snapshots, summarize changes, and approve or request changes. |
argos-upload |
When and how to share a screenshot or a screen recording by link, how to embed it so a pull request actually renders it, and how to read back the comments a human pinned on it. |
Installation
npx skills add https://argos-ci.com
This installs every skill Argos publishes. The skill content lives in the argos-javascript repository.
Usage
Reference a skill in your prompt to activate it:
Use $argos-pr-review to review this pull request with its Argos build.
https://github.com/acme/app/pull/123
For the full workflow — tokens to set, what the agent does, and how to phrase prompts when your assistant does not support skills — see Review builds with AI agents.
The argos-cli skill also covers the flakiness commands, so an agent can investigate an unstable test and silence a change it can't fix — see Fix flaky tests with AI agents.
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 · 32 tokens per session scan A 404e3747a961
agent-skills is an agent published in the GitHub repository argos-ci/docs (5 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 494 once invoked, about $0.0002 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 agents, from other repositories
junior-developer
Adversarial-collaboration generalist, three to five years in, who assumes every plan, design, requirement, code change, or in-flight discussion hides assumptions, muddied scope, and claims made without evidence. Works in two modes: artifact-review over completed plans, PRDs, ADRs, design docs, code branches, and…
grader
Evaluate expectations against an execution transcript and outputs.
create
Agent "create" from thevibeworks/claude-code-docs, covering create agent, headers, body parameters, returns and example.
execute
Execute a development plan created by the plan agent — spawn parallel subagents per phase, test, and ship.
sw-architect
System Architect for writing plan.md with architecture decisions and component design. Use for increment technical planning during sw:increment orchestration.
abap-functional-researcher
L2 functional researcher of the abapwiki knowledge base. For a slice (business process) it reads the members' L1 pages and the dependency graph, identifies the functional GAPS (why it exists, who launches it, semantics of the Z fields and of the magic numbers, standard integration, data lifecycle), classifies them and…