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/greatmark/fable-field-guide-skills/implementation-notesnpx skills add GreatMark/fable-field-guide-skills --skill implementation-notesgit 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/implementation-notes)<a href="https://agentmods.dev/skills/greatmark/fable-field-guide-skills/implementation-notes"><img src="https://agentmods.dev/badge/skills/greatmark/fable-field-guide-skills/implementation-notes.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 | $0.00136 | $0.01427 |
| Opus 5 | $0.00068 | $0.00714 |
| Sonnet 5 | $0.00027 | $0.00285 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
implementation-notes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Notes
No plan survives contact with the codebase. Log what changed and why, without stopping the work.
Workflow
- At the start of implementation, create
implementation-notes.mdin the project root. If the file already exists, do not overwrite it — when its latest section is this same task, keep appending there; otherwise append a new# Implementation Notes — <task name> (<YYYY-MM-DD>)section at the end, opening with the same AGENT comment as the template below. Do not commit the file unless the user asks (once committed, the exclude stops applying — keep later edits out of unrelated commits). If this is a git repo, exclude it locally (not.gitignore— that would show up in the diff):n=implementation-notes.md; p="$(git rev-parse --git-path info/exclude 2>/dev/null)" && { mkdir -p "$(dirname "$p")" && { grep -qxF "$n" "$p" || echo "$n" >> "$p"; }; } 2>/dev/null || echo "note: could not exclude $n — leaving it untracked, never staging it"(worktree-safe; if the write is blocked, leave the file untracked and never stage it). Structure:
# Implementation Notes — <task name> (<YYYY-MM-DD>)
<!-- AGENT (re-read this even after context compaction): running log for this
task. (1) Log every decision and deviation immediately, 1-3 lines each;
deviations as: plan said / found / did instead / why. (2) Re-read this file
before every commit and after each completed todo; log anything the plan
didn't say before moving on. (3) Never commit or stage this file. (4) Before
the session ends: re-read it, give the user a digest of THIS task's
Deviations and Open Questions, and remind them to feed this file into the
next planning round (or pitch-explainer / change-quiz). Full workflow: read
the implementation-notes skill. -->
## Context
Links to the plan/spec/prototype/taking list this run is based on (e.g.
implementation-plan.md, ./design-directions/). If the plan lives only in
chat, restate its one-line goal and key decisions here.
## Decisions
Choices made where the plan was silent. One line each: what + why.
## Deviations
Where reality forced a change from the plan.
Each entry: what the plan said / what was found / what was done instead / why.
## Surprises & Open Questions
Edge cases, dead code, wrong assumptions in the plan — anything the next
planning session should know.
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 · 110 lines · 136 tokens per session scan A 25b877c29d88
implementation-notes is a skill published in the GitHub repository GreatMark/fable-field-guide-skills (9 stars, last pushed 25d ago), licensed MIT. It adds 136 tokens to every session and 1,427 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
documentation-and-adrs
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
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-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
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
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.