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 ctxpipe-ai/ctxpipe --skill ownershipgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/ownership)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/ownership"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/ownership/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/ctxpipe-ai/ctxpipe/ownership"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/ownership.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 | $0.00041 | $0.00529 |
| Opus 5.5 | $0.00016 | $0.00212 |
| Sonnet 5.5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
ownership 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 4d 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.
What it actually says
ownership
The host runs this skill as a plain command, once for each repository, on the assembled ref after the root steps. No model runs it.
- The host writes
/ctxpipe/step.jsonand the context index, as for each step. - The host writes the root-to-file map (ADR-052 section 6) and runs
node /ctxpipe/skills/ownership/scripts/ownership.mjs --source /ctxpipe/source/<handle> --source-url <url> --source-path <path> --roots <root-to-file map>.--rootsis necessary. - The script reads the first of
.github/CODEOWNERS,CODEOWNERS, anddocs/CODEOWNERS. For each root, the last rule whose pattern covers the root folder gives the owners. Patterns follow the gitignore rules: a slash at the start or in the middle anchors a pattern, and a pattern that matches a folder covers each folder below it. A file pattern (for example*.md) does not own a root. Only GitHub teams (@org/team) become team files; a person and an email address do not. - A rule with a pattern or an owner that the script cannot quote safely is listed in
skipped. It stays as a rule with no owner, so an earlier rule does not take its roots. - The team file gets an
OWNSclaim to each mapped file of the root. Only a mapped file whosesourceshold the source path (--source-path) counts. - For each team, the script finds the context file of kind
Teamwith the nameorg/teamin the context index, and adds new claims and new## Relatedlines to it. When there is no such file, it createsknowledge/teams/<org>-<team>.md. When a file with another name has that path, or two teams get one file, the script skips the team and lists it inskipped. - It writes at most 30 files in a step. When more files wait, the result has
"more": true, and the host runs the skill again on the new base. - It writes the staged tree and
/ctxpipe/out/patch.json, and a summary that matchesschema.jsonto stdout.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 18 lines · 41 tokens per session scan A cea560317270
ownership is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 529 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 2026-10-21.
Other skills, from other repositories
qa-review
Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.
consistency-check
Detect inconsistencies across related artefacts and governance constraints. Activate after story generation, after plan preparation, before implementation, or after remediation attempts. Reports issues — does not fix them.
tendril-review
Comprehensive post-change review of all modified files. Checks for code smells, cleanup opportunities, unnecessary legacy support, missing tests, broken tests, and obsolete tests. Use after a big change to leave the codebase in better health.
code-review
Performs multi-dimensional code review covering security, quality, spec compliance, and maintainability. Used when reviewing completed implementations or before merging changes.
maxsim-simplify
Reviews changed code for reuse opportunities, quality issues, and efficiency improvements, then fixes actionable items. Used after implementing features or when code feels over-engineered.
improve-codebase-architecture
Surface deepening refactors that turn shallow modules into deep ones, informed by CONTEXT.md and docs/adr/. Use when the user asks to improve architecture, find refactor candidates, raise testability, or make a codebase more agent-navigable. Skip for single localized fixes.