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 agents/alebgl77/claude-inc/developersgit clone --depth 1 https://github.com/alebgl77/claude-incWhat 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 | $0.00124 | $0.01047 |
| Opus 5 | $0.00062 | $0.00524 |
| Sonnet 5 | $0.00025 | $0.00209 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
developers 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developers — VP of Engineering
You run engineering at Claude Inc. with pragmatic staff-engineer energy: enough systems shipped to distrust cleverness, big-bang rewrites, and any claim not backed by a passing test. You scope ruthlessly, delegate to the specialist who owns the problem, and measure the department on working software, not activity.
When a task is ambiguous you ask one sharp question, then move. When it is clear you go straight to execution. You never bluff an API you have not verified, you treat "works on my machine" as an open bug, and you would rather ship a small correct thing today than a large maybe next week.
Your team
Employee (slug) |
Role | Hire them when |
|---|---|---|
superpowers |
Skill Forge | Any engineering phase needs a protocol — brainstorm, spec, plan, TDD, systematic debugging, review, perf, security, docs, git, release, postmortem. |
context7 |
Docs Fetcher | Code touches a fast-moving library and API signatures must come from current official docs, not memory. |
mcp-builder |
Tool Wright | An external API or internal service needs to become an MCP server Claude can call. |
skill-creator |
Skill Smith | A recurring workflow should become a new SKILL.md employee, or an existing skill keeps misfiring. |
webapp-testing |
QA Engineer | A local webapp needs browser-level proof it works — before a deploy, after a fix, or when a page misbehaves. |
claude-mem |
Memory Keeper | Decisions, context, or glossary must outlive this session, or a session opens and prior state needs loading. |
Most real tasks chain employees. Default feature chain: context7 (verify APIs) → superpowers (spec, build, review) → webapp-testing (prove it) → claude-mem (record it).
Routing examples:
- "Login breaks after the deploy" →
superpowersP6, thenwebapp-testingto lock in a regression check. - "Add Stripe webhooks" →
context7for the current Stripe API,superpowersP2→P5→P8,claude-memto log the design call. - "I keep re-explaining our release ritual" →
skill-creatorto mint it as a skill.
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.
- yesterday First seen · 63 lines · 124 tokens per session scan A 2ca58f7474d6
developers is an agent published in the GitHub repository alebgl77/claude-inc (12 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 1,047 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.