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 GreatMark/fable-field-guide-skills --skill field-guidegit clone --depth 1 https://github.com/GreatMark/fable-field-guide-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/greatmark/fable-field-guide-skills/field-guide)<a href="https://agentmods.dev/skills/greatmark/fable-field-guide-skills/field-guide"><img src="https://agentmods.dev/badge/skills/greatmark/fable-field-guide-skills/field-guide/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/greatmark/fable-field-guide-skills/field-guide"><img src="https://agentmods.dev/badge/skills/greatmark/fable-field-guide-skills/field-guide.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 | $0.00133 | $0.00875 |
| Opus 5 | $0.00067 | $0.00438 |
| Sonnet 5 | $0.00027 | $0.00175 |
| Haiku 4.5 | $0.00013 | $0.00088 |
Grade A, and why
field-guide 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Field Guide
Route by the unknown blocking the user right now, then read and follow that skill. Unsure which: three quick questions — unfamiliar ground? decisions only the user can make? needs to see something? Enter at the current stage (an outside plan or spec counts as approved); don't re-run earlier stages. When several rows apply, drop rows their "Not for" clauses reject; take the earliest stage neither done nor explicitly skipped by the user (done: approval words, an artifact, or time phrasing — never route backwards past completed work). design-directions vs reference-hunt: a fork, not a sequence. Chained requests run each stage in order — never silently drop later parts. Mis-routed? Switch — "Not for" clauses decide; keep anything produced.
Routing table
| Stuck on | Skill |
|---|---|
| Nothing — no unknown blocks it; small task, clear path (没有未知数阻塞的小事) | none — just do the work |
| Unfamiliar area before starting; hidden pitfalls (unknown unknowns; 开工前不熟悉、怕有暗坑) | blindspot-pass |
| Known ambiguities the user must decide (known unknowns; 已知模糊点要用户拍板；"有不确定可以问我"不算) | interview-me |
| Can't say what they want but would recognize it; no concrete reference (说不出想要什么、看到能认出、无参照物) | design-directions |
| Has a concrete reference: "make it like that" (有具体参照物、要像它那样) | reference-hunt |
| Discussion converged, ready to build; reviewable plan first (讨论收敛要动手、先出可评审方案) | implementation-plan |
| Implementing an approved plan (按批准的方案实现中) | implementation-notes |
| Verify your own understanding of this change set before merging (合并前验证自己真懂、怕有没看出来的坑) | change-quiz |
| Quiz failed on a real defect (quiz 暴露实现有误) | fix + log in implementation-notes, re-quiz; plan wrong → implementation-plan |
| Persuade or explain to others after the work (说服不在环内的评审者、跟团队讲清楚这次改动；纯科普不算) | pitch-explainer |
Artifact contract (every skill in this family follows it)
interview-decisions.md,porting-checklist.md,implementation-plan.md,implementation-notes.md,change-report.html,pitch-<topic>.htmllive in the project root (in a monorepo: the affected package's root); prototypes live in./design-directions/. Parallel tasks: append a titled section (notes) or suffix the filename with a task slug.- Never commit artifacts unless the user explicitly asks (change-report.html: never); exclude them via each member skill's worktree-safe command; if that write fails, fall back to leaving them untracked and tell the user.
- Artifacts are caches: if one is lost, rebuild it from the session history or rerun its skill — never block on a missing artifact.
- Artifacts are written in the language of the conversation (pitch may follow the reviewer's language).
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.
- 9d ago First seen · 56 lines · 133 tokens per session scan A 2334538e162b
field-guide is a skill published in the GitHub repository GreatMark/fable-field-guide-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 875 once invoked, about $0.0007 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
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
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.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
create-slack-app
Use when a developer wants to create, scaffold, or bootstrap a new Slack app or agent from scratch with the Slack CLI. Covers prerequisites, sandbox setup, authentication, and creating + running a project from a Bolt (JS or Python) template locally. Trigger on "create a Slack app", "new Bolt app", "start a Slack…