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/andrzejchm/fdb/implementing-fdb-featuresnpx skills add andrzejchm/fdb --skill implementing-fdb-featuresgit clone --depth 1 https://github.com/andrzejchm/fdbWrote 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/andrzejchm/fdb/implementing-fdb-features)<a href="https://agentmods.dev/skills/andrzejchm/fdb/implementing-fdb-features"><img src="https://agentmods.dev/badge/skills/andrzejchm/fdb/implementing-fdb-features.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 | $0.00044 | $0.03476 |
| Opus 5 | $0.00022 | $0.01738 |
| Sonnet 5 | $0.00009 | $0.00695 |
| Haiku 4.5 | $0.00004 | $0.00348 |
Grade A, and why
implementing-fdb-features 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 5d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow checklist
Copy this into mcp_Todowrite at the start of every feature session and tick off each item as you go:
Capture:
- [ ] Read issue in full and claim it (bd update <id> --claim)
Setup:
- [ ] Create worktree (mcp_Git-worktree create <name> main)
- [ ] Run task setup in the worktree
Implementation:
- [ ] Core models: lib/core/commands/<name>/<name>_models.dart
- [ ] Core verb: lib/core/commands/<name>/<name>.dart
- [ ] CLI adapter: lib/cli/adapters/<name>_cli.dart
- [ ] Register case + usage string in bin/fdb.dart
- [ ] fdb_helper handler (if needed): packages/fdb_helper/lib/src/handlers/<name>_handler.dart
- [ ] Register in fdb_binding.dart (if handler added)
- [ ] Test app changes in example/test_app/lib/main.dart (if needed)
Taskfile tests:
- [ ] test:<command> task added following existing pattern
- [ ] Task added to smoke sequence
- [ ] task analyze passes (dart analyze + dart format + flutter analyze)
Docs:
- [ ] README.md — commands table
- [ ] .agents/skills/testing-fdb/SKILL.md — individual test list
- [ ] lib/skill/SKILL.md — usage examples (load creating-opencode-skills skill first)
- [ ] doc/agent-scenarios.md — add scenario for the new/changed command
Agent scenarios (delegated):
- [ ] Spawn scenarios agent with worktree path + scenario IDs to run
- [ ] Triage every failure: scenario doc fix, pre-existing bug, or regression
- [ ] User approves triage findings before any bug issues are filed
- [ ] All failures resolved (fixed, scenario corrected, or filed as separate bugs)
Review loop (delegated):
- [ ] Spawn reviewing-fixing-loop agent
- [ ] All findings resolved or triaged
Checks (delegated):
- [ ] Spawn checks agent (dart analyze + flutter analyze + dart format)
- [ ] All clean
Platform tests (ALL mandatory before PR):
- [ ] macOS — task test:<command> passes
- [ ] Android physical — task test:<command> passes
- [ ] iOS simulator — task test:<command> passes
- [ ] Full smoke suite: task smoke (Android)
PR:
- [ ] Load humanizing-ai-text skill before writing PR body
- [ ] Load managing-pr-descriptions-global skill
- [ ] Push branch
- [ ] Open PR (gh pr create)
- [ ] CI green (gh pr checks --watch)
Merge:
- [ ] bd close <id> + copy issues.jsonl into worktree + commit + push
- [ ] gh pr merge --squash --delete-branch
- [ ] Remove worktree (mcp_Git-worktree remove <name>)
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.
- 5d ago First seen · 385 lines · 44 tokens per session scan A dcc1a8e947f5
implementing-fdb-features is a skill published in the GitHub repository andrzejchm/fdb (46 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 3,476 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…