oversee

A controlled workflow for taking one GitHub issue from planning to a reviewed pull request, with a person approving the plan before coding starts.

In plain words
What is it for?
Use it for one issue at a time, especially changes involving architecture, language handling, public interfaces, or other important design decisions.
Why use it?
It adds a clear human checkpoint before work begins and checks the plan and finished changes for problems. This helps when choosing the wrong approach would be costly.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/optave/ops-codegraph-tool/oversee
Any agent
npx skills add optave/ops-codegraph-tool --skill oversee
Clone the repo
git clone --depth 1 https://github.com/optave/ops-codegraph-tool

Made for: Claude Code, Codex.

Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00143 $0.16726
Opus 5 $0.00072 $0.08363
Sonnet 5 $0.00029 $0.03345
Haiku 4.5 $0.00014 $0.01673

Measured yesterday against content hash cacc7e17d925, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

oversee scanned grade D with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. **Auto-accept ("auto mode") — CONFIRM, not detect.** There is no env var or settings field that reports the **live** permission mode: it is runtime state toggled with shift+Tab. It can only be confirmed, never detecte

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Cleanup.** State is safe to re-read and safe to delete: a fresh invocation re-derives everything it needs from GitHub. Remove it with `rm -rf .codegraph/oversee` once the execute PR is merged. Leaving it costs nothing.
.claude/skills/oversee/SKILL.md · 947 lines

How it starts

The opening of the file, as written. The whole thing — 947 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oversee — human-gated, single-issue delivery for codegraph

/oversee takes one GitHub issue from "nobody has planned this" to "a verified, reviewer-clean PR waiting for a human merge", with exactly one human decision in the middle: does this plan get built? Everything else — planning, adversarial plan review, reviewer sweeps, the build, independent verification, review convergence — runs automatically.

It is the human-in-the-loop counterpart to /fixer. The two are complementary, not interchangeable:

/fixer /oversee
Scope the whole qualifying backlog, in batches exactly one issue
Plan none — solve directly a committed plan doc, reviewed and human-approved before any code
Human decision none until the final report one: tick the approval box
Merge merges each PR itself never merges — the human does

Use /oversee for work where getting the approach wrong is expensive: anything touching the dual-engine boundary, resolution semantics, the language registry, a public API, or an architectural decision. Use /fixer for a backlog of self-contained fixes.

You are split in two:

  • You (this skill) are the gating brain. You preflight the session config, route the run, run a readiness check, drive the human approval gate, verify its provenance, validate plan freshness, and reconcile the reviewer after execution. You never write product code.
  • oversee-dispatch is the execution engine. You hand it one task plus a phase, and it runs that half of the pipeline.
/oversee #<issue>    ─preflight─▶ sync main ─▶ readiness ─▶ PLAN ─▶ critic (advisory, revise-in-place)
                                                                 ─▶ plan-sweep ─▶ [Plan] PR + ✋ approval box ─▶ STOP
                                                                                   │  (a human ticks the box)
/oversee #<plan-PR>  ─preflight─▶ sync main ─▶ box ticked? ─▶ provenance? ─▶ freshness gate (Sonnet subagent)
                                                                 ├─FRESH──▶ EXECUTE (pinned to approved SHA) ─▶ VERIFY ─▶ execute-sweep ─▶ reconcile ─▶ STOP (human merges)
                                                                 ├─NARROW─▶ patch the plan in place ─▶ re-stamp the gate ─▶ STOP (needs a fresh tick)
                                                                 └─STALE──▶ carry-forward ─▶ close the [Plan] PR ─▶ re-PLAN ─▶ STOP (needs a fresh tick)

Two things make this worth running instead of just asking an agent to fix an issue:

  1. A preflight config gate runs before any compute is spent.
  2. The human is the plan gate, and the gate cannot be forged. The critic is advisory — its verdict is printed next to the checkbox, it never auto-advances. EXECUTE runs only after a human ticks the box, and only when a commit status the PR body's author cannot write proves the gate was installed by an /oversee run for that exact plan head.

Read the full file on GitHub · 947 lines

Changes

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.

  1. yesterday First seen · 947 lines · 143 tokens per session scan D cacc7e17d925

Subscribe to this mod's changes

oversee is a skill published in the GitHub repository optave/ops-codegraph-tool (92 stars, last pushed 3d ago), licensed Apache-2.0. It adds 143 tokens to every session and 16,726 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

codespaces

Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal…

diskd-ai/codespaces · 74 tokens

security-triage

Turn a large codebase into a short, ranked reading list of security-relevant code paths worth a human researcher's time, using the flyto-indexer MCP tools. Use when asked to find, prioritize, or triage potential vulnerabilities / taint flows / attack surface in a repository indexed (or indexable) by flyto-indexer …

flytohub/flyto-indexer · 105 tokens

devlens

Understand a codebase with the DevLens MCP — TypeScript, JavaScript, Python, Go, Rust, or Java (incl. React/Next.js/Node, FastAPI/Flask/Django, Spring Boot, Gin/Echo/chi/net-http, axum/actix/rocket). Query a precomputed graph of nodes (components, hooks, functions, classes, methods, structs, traits, routes) and typed…

devlensio/devlensOSS · 0 tokens

archon

Multi-language dependency impact analysis for Java, JS/TS, and Python codebases. Answers "if I change this, what breaks?" Run /archon diff before refactoring, /archon analyze for full dependency maps.

Schr0d/Archon · 48 tokens

codebase-intelligence

Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.

bntvllnt/codebase-intelligence · 54 tokens

repomix

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

yamadashy/repomix · 58 tokens