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/typefox/agent-skills/agent-experiencenpx skills add TypeFox/agent-skills --skill agent-experiencegit clone --depth 1 https://github.com/TypeFox/agent-skillsWrote 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/typefox/agent-skills/agent-experience)<a href="https://agentmods.dev/skills/typefox/agent-skills/agent-experience"><img src="https://agentmods.dev/badge/skills/typefox/agent-skills/agent-experience.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 | $0.00179 | $0.05813 |
| Opus 5 | $0.00089 | $0.02906 |
| Sonnet 5 | $0.00036 | $0.01163 |
| Haiku 4.5 | $0.00018 | $0.00581 |
Grade A, and why
agent-experience 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 4d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Experience (AX)
AX is the experience AI agents have when working in a repository — how easily they can access, understand, verify, and safely change it. Two reframings drive everything in this skill. First, onboarding happens at the start of every task: a human onboards once, an agent re-onboards every session, so everything a new hire needs in week one, the agent needs in minute one, on every run. Second, hallucination is what inference looks like when context is missing: when an agent invents a build command or misuses an internal API, that is not a model defect to tolerate — it is an AX defect to fix.
The honest test — the single success criterion behind every artifact this skill produces: an agent given a real ticket, with no human help, reliably reaches a green verification suite and produces a diff a reviewer accepts. Optimize for that. Readiness checklists and scores are diagnostics for spotting neglect, never targets to maximize.
Vocabulary: write "AX" and "agent-ready" in everything you produce. When reading sources or searching the web, also recognize the synonyms: context engineering (the superset term — this skill is its repo-side slice), harness engineering (in its repo-side sense), agent readiness, agent legibility, ambient affordances. Generated artifacts never say "harness" — that word collides with the agent-runtime meaning.
The control system in brief
Treat the repo-side AX setup as a control system that regulates the codebase toward its desired state. Two control directions × two execution modes give a 2×2 that classifies everything you find or create:
| Guides (feedforward — steer before the agent acts) | Sensors (feedback — verify after it acts) | |
|---|---|---|
| Computational (deterministic, fast, cheap — run on every change) | one-command bootstrap, task-runner command surface, scaffolding, codemods, generated reference docs, deterministic dev env | type checks, linters, tests + coverage, structural/dependency rules, mutation testing, secret scanners, the build |
| Inferential (LLM-run, semantic, costly — run at gates or on a schedule) | AGENTS.md, skills, docs/, ADRs (architecture decision records — short, versioned docs capturing one decision, its context, and its consequences), specs, code-level discoverability | review skills, modularity reviews, security/data reviews, doc-gardening, janitor/GC agents |
What ships with it
60 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.
- assets/adr-template.md 1.8 KB
- assets/AGENTS.template.md 3.9 KB
- assets/exec-plan-template.md 1.3 KB
- assets/product-spec-template.md 2.5 KB
- evals/evals.json 38 KB
- evals/files/bloated-agents/AGENTS.md 8.6 KB
- evals/files/bloated-agents/Makefile 112 B
- evals/files/bloated-agents/pyproject.toml 294 B
- evals/files/bloated-agents/README.md 276 B
- evals/files/bloated-agents/scripts/gen_fixtures.py 677 B runs code
- evals/files/bloated-agents/shiftplan/__init__.py 62 B runs code
- evals/files/bloated-agents/shiftplan/data/holidays.json 338 B
- evals/files/bloated-agents/shiftplan/payroll.py 535 B runs code
- evals/files/bloated-agents/shiftplan/scheduler.py 948 B runs code
- evals/files/bloated-agents/tests/__init__.py 0 B runs code
- evals/files/bloated-agents/tests/test_payroll.py 623 B runs code
- evals/files/bloated-agents/tests/test_scheduler.py 1.0 KB runs code
- evals/files/disputed-behavior/AGENTS.md 977 B
- evals/files/disputed-behavior/CLAUDE.md 11 B
- evals/files/disputed-behavior/Makefile 131 B
- evals/files/disputed-behavior/notes/billing-increments-thread.md 1.6 KB
- evals/files/disputed-behavior/README.md 454 B
- evals/files/disputed-behavior/sample-data/entries.csv 242 B
- evals/files/disputed-behavior/tests/__init__.py 0 B runs code
- evals/files/disputed-behavior/tests/test_invoice.py 881 B runs code
- evals/files/disputed-behavior/tests/test_rounding.py 887 B runs code
- evals/files/disputed-behavior/tickbill/__init__.py 0 B runs code
- evals/files/disputed-behavior/tickbill/cli.py 789 B runs code
- evals/files/disputed-behavior/tickbill/csvin.py 1.2 KB runs code
- evals/files/disputed-behavior/tickbill/invoice.py 834 B runs code
- evals/files/disputed-behavior/tickbill/rounding.py 402 B runs code
- evals/files/drifted-agents/AGENTS.md 1.2 KB
- evals/files/drifted-agents/CHANGELOG.md 539 B
- evals/files/drifted-agents/changes/101-empty-fragments.md 70 B
- evals/files/drifted-agents/changes/104-sort-order.md 66 B
- evals/files/drifted-agents/CLAUDE.md 1.1 KB
- evals/files/drifted-agents/Makefile 117 B
- evals/files/drifted-agents/pyproject.toml 146 B
- evals/files/drifted-agents/README.md 568 B
- evals/files/drifted-agents/relnotes/__init__.py 22 B runs code
- evals/files/drifted-agents/relnotes/assemble.py 1.4 KB runs code
- evals/files/drifted-agents/scripts/build_changelog.py 1.4 KB runs code
- evals/files/drifted-agents/tests/__init__.py 0 B runs code
- evals/files/drifted-agents/tests/test_assemble.py 1.7 KB runs code
- evals/files/retrofit-cli/.gitignore 20 B
- evals/files/retrofit-cli/package.json 265 B
- evals/files/retrofit-cli/README.md 523 B
- evals/files/retrofit-cli/scripts/lint.mjs 612 B runs code
- evals/files/retrofit-cli/src/cli.js 948 B runs code
- evals/files/retrofit-cli/src/parse.js 967 B runs code
- evals/files/retrofit-cli/src/render.js 805 B runs code
- evals/files/retrofit-cli/test/parse.test.js 639 B runs code
- evals/files/retrofit-cli/test/render.test.js 623 B runs code
- references/agents-md.md 10 KB
- references/audit-playbook.md 14 KB
- references/docs-structure.md 23 KB
- references/interview.md 12 KB
- references/techniques.md 23 KB
- scripts/check_docs.py 56 KB runs code
- scripts/test_check_docs.py 47 KB runs code
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.
- 4d ago First seen · 173 lines · 179 tokens per session scan A 4d45070b7d28
agent-experience is a skill published in the GitHub repository TypeFox/agent-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 179 tokens to every session and 5,813 once invoked, about $0.0009 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 skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…