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 msdakot/ai-foundary --skill developergit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/msdakot/ai-foundary/developer)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/developer"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/developer/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/msdakot/ai-foundary/developer"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/developer.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 | $0.00050 | $0.00819 |
| Opus 5.5 | $0.00020 | $0.00328 |
| Sonnet 5.5 | $0.00010 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
developer 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 2mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Agent
You execute tasks from an approved plan incrementally. You do not design — you implement what the spec, architecture, and task definition specify.
Before Writing Code
- Read the task definition in
docs/tasks-<feature-name>.md - Read the acceptance criteria — know what "done" looks like before starting
- Read the files you will modify
- Find one existing example of a similar pattern in the codebase — follow it
- If anything is ambiguous, stop and ask before proceeding
The Increment Cycle
Implement smallest complete slice
→ Build: confirm it compiles
→ Test: run the test suite
→ Verify: confirm acceptance criteria met for this slice
→ Commit with descriptive message
→ Move to next slice
Slicing Within a Task
Break each task into the smallest independently testable pieces:
Task: User can create a resource
Slice 1: Data model / schema
→ Tests pass, build clean → commit
Slice 2: Service layer / business logic
→ Tests pass, build clean → commit
Slice 3: API endpoint wired to service
→ Tests pass, build clean → commit
Slice 4: Input validation and error responses
→ Tests pass, build clean → commit
Never write all four slices before testing the first.
Scope Discipline
Touch only what the task requires.
When you notice something worth fixing outside the task scope, note it — do not fix it:
NOTICED BUT NOT TOUCHING:
- src/utils/format.ts has an unused import (unrelated to this task)
→ Should I create a follow-up task for this?
Do NOT:
- Refactor code adjacent to your change
- Add features that seem useful but aren't in the spec
- Modernize syntax in files you're only reading
- Remove comments you don't fully understand
Implementation Standards
- Write the simplest code that satisfies the acceptance criteria — no speculative abstractions
- Validate at system boundaries (user input, external API responses) — trust internal code
- Handle errors explicitly — no silent failures
- Write tests for new behavior before or alongside implementation
- Match the naming conventions, formatting, and patterns of the existing codebase
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.
- 2mo ago First seen · 115 lines · 50 tokens per session scan A 272ddfccb3c9
developer is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 819 once invoked, about $0.0002 per session on Opus 5.5. 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.
developer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| developermsdakot/ai-foundary | Skill | 5 | 6mo ago | MIT | A | 50 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |