Borrowing it
Nothing to install: this file belongs to cognitx-leyton/codegraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cognitx-leyton/codegraph/main/.claude/commands/who-owns.mdgit clone --depth 1 https://github.com/cognitx-leyton/codegraphWrote 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/commands/cognitx-leyton/codegraph/who-owns)<a href="https://agentmods.dev/commands/cognitx-leyton/codegraph/who-owns"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/who-owns/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/commands/cognitx-leyton/codegraph/who-owns"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/who-owns.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 | $0.00016 | $0.00670 |
| Opus 5.5 | $0.00006 | $0.00268 |
| Sonnet 5.5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
who-owns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/who-owns <path>
Path must match :File.path exactly — repo-root-relative with forward slashes (e.g. codegraph/codegraph/loader.py, not absolute, not with a leading ./).
Joins three ownership edges written by the Phase-7 ownership pass:
| Edge | Source | Columns |
|---|---|---|
LAST_MODIFIED_BY |
most-recent commit from git log |
author name, email, timestamp |
CONTRIBUTED_BY |
all authors for the file, with commit counts | roll-up of top 5 |
OWNED_BY |
CODEOWNERS file |
team name(s) |
What this does
codegraph query "
MATCH (f:File {path: '$ARGUMENTS'})
OPTIONAL MATCH (f)-[lm:LAST_MODIFIED_BY]->(last:Author)
OPTIONAL MATCH (f)-[c:CONTRIBUTED_BY]->(co:Author)
OPTIONAL MATCH (f)-[:OWNED_BY]->(t:Team)
WITH f, last, lm, t, co, c
ORDER BY c.commits DESC
WITH f,
last,
lm,
collect(DISTINCT t.name) AS teams,
collect({author: co.name, email: co.email, commits: c.commits})[..5] AS top_contributors
RETURN f.path AS file,
last.name AS last_modified_by,
last.email AS last_email,
lm.at AS last_modified_at,
teams,
top_contributors
"
Caveats
- Requires ownership indexing.
/graph-refreshruns with--skip-ownershipby default (it's ~30s slower with it). Iflast_modified_bycomes back null andtop_contributorsis[{author: null, ...}], re-index without the flag:codegraph index . -p codegraph/codegraph -p codegraph/tests --no-wipe CODEOWNERSmust be present. If the repo has noCODEOWNERSfile (or.github/CODEOWNERS/docs/CODEOWNERS), theteamscolumn will be empty. That's not a bug — it's the absence of team-level ownership metadata.- Path has to match exactly. Use
/graph "MATCH (f:File) WHERE f.path CONTAINS 'loader' RETURN f.path"if you're not sure of the stored path. - Author email is the join key (
CREATE CONSTRAINT author_email ... UNIQUE). If the same person commits under multiple emails, they appear as separate authors.
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 · 59 lines · 16 tokens per session scan A 8b2dae2cf39b
who-owns is a command published in the GitHub repository cognitx-leyton/codegraph (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 670 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
review
Architecture-aware code review with Pharaoh.
feedback
A design-stage security review for product requirement documents and other planning documents; a PRD is a document describing what a product should do.
va
A read-only security review of a codebase across eight architecture areas, with findings checked against file-and-line evidence.
compliance
A follow-up security check that verifies whether earlier findings were fixed and, depending on the selected mode, looks for new problems.
pentest
A read-only penetration-testing command for examining source code from an attacker’s perspective and producing proof-of-concept checks. Penetration testing is authorized security testing that tries to verify exploitable weaknesses.
run
A security-workflow coordinator that turns a natural-language request into a plan involving code review, verification, attack testing, or reporting.