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 anthroos/openexp --skill d49e0997git clone --depth 1 https://github.com/anthroos/openexpWrote 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/anthroos/openexp/d49e0997)<a href="https://agentmods.dev/skills/anthroos/openexp/d49e0997"><img src="https://agentmods.dev/badge/skills/anthroos/openexp/d49e0997/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/anthroos/openexp/d49e0997"><img src="https://agentmods.dev/badge/skills/anthroos/openexp/d49e0997.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 | $0.00000 | $0.01602 |
| Opus 5 | $0.00000 | $0.00801 |
| Sonnet 5 | $0.00000 | $0.00320 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
openexp:ivan-pasichnyk:inbound-acquisition-with-free-pilot 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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenExp Experience — Ivan Pasichnyk · Inbound Acquisition Trajectory
You have access to a published experience pack authored by Ivan Pasichnyk (handle: ivan-pasichnyk). The pack ships raw: an anonymized 26-step trajectory plus a facts-only meta.yaml. There is no applies_when, no searchable_summary, no author grade or grade reason. Those are interpretations. They belong to the reader, not the publisher.
Why raw
The publisher's interpretation is one Claude's read of the timeline at the moment of publication, biased by what worked for that one author at that one moment. Different readers have different contexts and will draw different signals from the same events. So the publisher hands over the timeline; the reader's Claude does the matching, on the fly, against the reader's actual situation.
How to use this pack
- Read
meta.yamlfirst. Facts only: outcome label (closed_won),closed_at: day_+57,duration_days,step_count,category_tokensthat appear in the timeline. - Read
trajectory.anonymized.yaml— 26 ordered steps fromrelative_day: 0(inbound discovery) torelative_day: +57(contract signed both sides). - Derive match on the user's actual situation. Look at the category tokens in
meta.yamland the structure of the trajectory. Decide whether the user's case is similar enough that step-level reference is useful. You do the matching here — the pack does not pre-declare when it applies. - Map the user's situation to one specific
relative_day. Find the closest step in the trajectory to where the user is in their own arc. - Cite by day with attribution. Frame as "in Ivan's trajectory, day +X was…", never "the rule is…".
Output style — DEFAULT QUIET MODE
Default reply mode is normal conversation, not a teleprompter. Most replies should be ≤3 short sentences, written the way a senior peer would talk — not as a structured report.
Do not, by default:
- dump match tables, scoring grids (✓/✗), or "X/4 ознак" breakdowns
- list every active lead with its match score
- enumerate options A/B/C/D
- repeat the outcome label after the first invocation
- include eyebrow labels like "1. Pack — підтверджую розуміння"
- preface answers with a four-step plan of what you'll output
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 98 lines · 0 tokens per session scan A 9dfaeb1a0724
openexp:ivan-pasichnyk:inbound-acquisition-with-free-pilot is a skill published in the GitHub repository anthroos/openexp (59 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,602 tokens. 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 2026-09-19.
Other skills, from other repositories
wiki-context-pack
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
evolve-lite:save-trajectory
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning.