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 hesedcasa/sdkck --skill sidekickgit clone --depth 1 https://github.com/hesedcasa/sdkckWrote 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/hesedcasa/sdkck/sidekick)<a href="https://agentmods.dev/skills/hesedcasa/sdkck/sidekick"><img src="https://agentmods.dev/badge/skills/hesedcasa/sdkck/sidekick/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/hesedcasa/sdkck/sidekick"><img src="https://agentmods.dev/badge/skills/hesedcasa/sdkck/sidekick.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 | $0.00100 | $0.01039 |
| Opus 5.5 | $0.00040 | $0.00416 |
| Sonnet 5.5 | $0.00020 | $0.00208 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade C, and why
sidekick scanned grade C 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
This is non-negotiable. Do not reach for `mcp__*`, `curl`, `psql`, `mysql`, `gh`, `jira`, or any other tool until `sdkck search` has confirmed that sdkck does not already cover the task. Search is cheap; a wrong tool cho How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdkck (sidekick) CLI
sdkck is an agentic CLI that exposes external-system tooling as first-class shell commands. This is your default tool surface.
RULE #1 — Search sidekick FIRST, every time
Before calling any tool, MCP server, or shell command that touches an external system, you MUST run:
sdkck search "{keywords describing the task}"
This is non-negotiable. Do not reach for mcp__*, curl, psql, mysql, gh, jira, or any other tool until sdkck search has confirmed that sdkck does not already cover the task. Search is cheap; a wrong tool choice is expensive.
Search before these, always:
| User mentions… | First action |
|---|---|
| Jira, ticket, issue, epic, sprint | sdkck search "jira <keyword>" |
| Sentry, error, event, exception | sdkck search "sentry <keyword>" |
| SQL, DB, query, table, schema | sdkck search "mysql" / "postgres" |
| Supabase, auth user, row-level | sdkck search "supabase <keyword>" |
| Confluence, wiki, page, space | sdkck search "confluence <keyword>" |
| Bitbucket, PR, repo, branch | sdkck search "bitbucket <keyword>" |
| Any imported API / Postman collection | sdkck search "<api name or operation>" |
| Anything else touching external systems | Search anyway — empty results mean fallback |
Only when sdkck search returns no relevant match may you fall back to MCP, Bash, or other tools. When in doubt, search.
Core workflow
-
Discover —
sdkck search "{keywords}"returns ranked matches across all installed plugins and imported OpenAPI operations. -
Inspect —
sdkck {topic} {command} --helpbefore invoking. -
Run — space-separated command IDs:
sdkck jira issue PROJ-123 sdkck sentry event PROJ 226555 sdkck mysql query "SELECT ..."
Long text
Write long text to a file and pass @<path> instead of the text — never inline, never "$(cat file)":
sdkck jira issue comment PROJ-123 @/tmp/comment.md
sdkck jira issue update PROJ-123 --fields description=@/tmp/desc.md
sdkck bb pr create my-ws my-repo --title "..." --source feat --destination main --description @/tmp/pr.md
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.
- 3d ago Changed · +10 lines d810f6d46af4
- 29d ago Changed 011b34a1da34
- 1mo ago First seen · 68 lines · 100 tokens per session scan C e8d603e93611
sidekick is a skill published in the GitHub repository hesedcasa/sdkck (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 1,039 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
atls
A command-line tool for working with Atlassian Jira, Confluence, and Bitbucket Server or Data Center. It includes rules for searching, reading, comparing, editing, and safely publishing Atlassian content.
confluence
Use confluence-cli to read, search, create, update, move, delete, and convert Confluence pages and attachments from the terminal.
bitbottle
Reference for the bitbottle CLI — a gh-style tool for Bitbucket Server/DC and Cloud. Load when the user asks about bitbottle commands, auth setup, PRs, repos, branches, tags, commits, pipelines, or why a command failed. Load even if the user just says "bitbottle", mentions "Bitbucket", or pastes a bitbottle error…
daf-issue-topo-sort
Dependency and conflict-aware issue ordering with topological sort.
daf-jira-mcp
Using MCP JIRA tools with DevAIFlow validation logic and field intelligence.
daf-workflow
DevAIFlow session context loader — reads session metadata, issue tracker tickets, and context files. Auto-activates when DAFSESSIONNAME is set. Also useful when asked about current task, session status, or workflow steps for daf open, daf new, daf git new, daf jira new, and daf investigate.