CocoIndex is an incremental data-processing engine that keeps code, documents, messages, PDFs, and videos continuously updated as context for AI agents and language-model applications. Engineers use it to build declarative Python pipelines that process only changed data, and its catalogue skills help coding agents work with CocoIndex correctly.
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 cocoindex-io/cocoindex --skill backportgit clone --depth 1 https://github.com/cocoindex-io/cocoindexWrote 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/cocoindex-io/cocoindex/backport)<a href="https://agentmods.dev/skills/cocoindex-io/cocoindex/backport"><img src="https://agentmods.dev/badge/skills/cocoindex-io/cocoindex/backport/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/cocoindex-io/cocoindex/backport"><img src="https://agentmods.dev/badge/skills/cocoindex-io/cocoindex/backport.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 | $0.00119 | $0.02097 |
| Opus 5.5 | $0.00048 | $0.00839 |
| Sonnet 5.5 | $0.00024 | $0.00419 |
| Haiku 4.5 | $0.00012 | $0.00210 |
Grade A, and why
backport 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backport a pull request to a release branch
How release branches work here
A minor release (1.2.0) is cut from main. A patch release (1.1.1) is cut
from the minor's release branch, release/1.1, which starts at the minor's tag
(v1.1.0) and moves only by backports: squash-merged pull requests that
cherry-pick commits already on main. The minor's release creates the branch
from its tag (dev/agent-skills/create-release/SKILL.md, step 7), and only
the newest minor's branch takes backports; an older one stays as it is (its
ruleset forbids deleting it).
A release branch has no merge queue. A pull request to it runs the full CI
tier on its own, and ci-gate must pass before it can be squash-merged.
AGENTS.md (Versioning) is the policy; this playbook is the procedure.
What qualifies. A change goes to a release branch when a user of the released minor needs it and it adds no way to call CocoIndex:
- a fix: released behavior that didn't match its documentation or intent (wrong results, lost or stale data, a crash, a hang, a security problem);
- a dependency bump that fixes an advisory in what the wheel ships (Rust crates of the engine, Python requirements of the package), not the development lockfile;
- a docs change that describes released behavior or improves the site (design, navigation, examples). Not docs of a feature that isn't released.
Never a new API, parameter, connector, source, CLI option or configuration key, experimental or not; not a refactor, an example, or CI or dev tooling, unless the branch's own CI needs it. A fix that is entangled with a feature is backported as the fix alone, adapted to the branch (step 3), not with the feature's commits for context.
A fix lands on main first. When it doesn't apply to main because the code
moved on, say so in the backport's pull request.
Needs gh authenticated with push access to cocoindex-io/cocoindex.
Placeholders: <pr> (the merged pull request's number), <sha> (its merge
commit on main), <X.Y> (the minor, e.g. 1.1).
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 Changed · -5 lines · -25 tokens per session dc90c5fafb2c
- 2d ago First seen · 194 lines · 144 tokens per session scan A 09212538f4b2
backport is a skill published in the GitHub repository cocoindex-io/cocoindex (11,832 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 2,097 once invoked, about $0.0005 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 2026-11-06.
backport compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backportcocoindex-io/cocoindex | Skill | 12k | today | Apache-2.0 | A | 119 | Claude Code, Codex |
| xberg-releasexberg-io/xberg | Skill | 9.6k | today | MIT | A | 16 | Claude Code, Codex |
| git-workflowvstorm-co/pydantic-deepagents | Skill | 1.1k | 8d ago | MIT | A | 17 | Claude Code, Codex |
| Release Notes GeneratorAgentEra/Agently | Skill | 1.7k | 25d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| pinned-release-checklistAgentEra/Agently | Skill | 1.7k | 25d ago | Apache-2.0 | A | 18 | Claude Code, Codex |
| Release ChecklistAgentEra/Agently | Skill | 1.7k | 25d ago | Apache-2.0 | A | 19 | Claude Code, Codex |
| Release Readiness ReviewerAgentEra/Agently | Skill | 1.7k | 25d ago | Apache-2.0 | A | 18 | Claude Code, Codex |