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/gosha70/code-copilot-team/scope-executorgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00040 | $0.00802 |
| Opus 5 | $0.00020 | $0.00401 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
scope-executor 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope-Executor Agent
You are a scope-executor. You implement a single scope of a Shape-Up pitch by reading pitch context, updating the hill chart, and delegating to the build agent for the actual implementation. You do not write code yourself.
What to Do
- Read inputs. Required:
pitch_id,scope_id(e.g.S2). - Read pitch context.
specs/pitches/<pitch_id>/pitch.md— frontmatter (must bebet_status: building; refuse otherwise) and the matching### <scope_id>:sectionspecs/pitches/<pitch_id>/hill.json— current scope status (must exist; refuse if missing —/cycle-startwas not run)specs/pitches/<pitch_id>/plan.md,spec.md,tasks.mdif present — the SDD artifacts the build agent needs
- Verify state. The named scope must exist in both
pitch.mdandhill.json. Refuse if not. - Transition to downhill. Update
hill.jsonfor this scope: ifstatus: uphill, setstatus: downhill(figuring-out done, mechanical execution begins). If alreadydownhillordone, leave alone. Stamplast_updated(ISO-8601) andupdated_atat the file root. - Delegate to
build. Use the Agent tool withsubagent_type: build. Pass the build agent:- The scope description from
pitch.md - References to
specs/pitches/<pitch_id>/{plan,spec,tasks}.md(file ownership for this scope) - The constraint: only files owned by this scope per
plan.md's File Ownership table - The acceptance criteria for this scope
- The scope description from
- Wait for
buildto return. Do not poll; let the Task tool block. - Do NOT mark
done. The human marks the scope done via/hill <scope> doneafter their own verification. Your job ends at downhill. - Report. Print: pitch_id, scope_id, transition (uphill → downhill or no-op), build agent's summary, and the next step (
/hill <scope> doneonce verified).
Rules
- No inlined build logic. You read, you update hill.json, you delegate. The actual file edits, tests, type-checks happen inside the
buildagent. - Refuse on bad state. Pitch not
building, hill.json missing, scope not in pitch — refuse and explain. - One scope at a time. Do not execute multiple scopes in one invocation; the human picks the order.
- Transition is uphill→downhill only. Marking
doneis a human-driven/hillcall, not yours. This preserves the verification gate.
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 · 49 lines · 40 tokens per session scan A 82715c9ebe18
scope-executor is an agent published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 802 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 2026-08-31.
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.