Sidecar is a terminal-based workspace for running AI coding agents alongside file trees, task issues, Git diffs, and Jira or GitHub resources in split panes. Developers use it to monitor agent sessions, inspect files and changes, manage workspaces, and handle tasks without leaving one shell. The catalogue entries extend or guide coding-agent workflows used with Sidecar.
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 marcus/sidecar --skill coordinate-agentsgit clone --depth 1 https://github.com/marcus/sidecarWrote 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/marcus/sidecar/coordinate-agents)<a href="https://agentmods.dev/skills/marcus/sidecar/coordinate-agents"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/coordinate-agents/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/marcus/sidecar/coordinate-agents"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/coordinate-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00106 | $0.03028 |
| Opus 5.5 | $0.00042 | $0.01211 |
| Sonnet 5.5 | $0.00021 | $0.00606 |
| Haiku 4.5 | $0.00011 | $0.00303 |
Grade A, and why
coordinate-agents 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 14d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinating another agent
Sidecar can start and coordinate a second agent in a shell it owns. The commands are headless, target-taking, and --json from birth, so everything here works from an ordinary shell with no TUI attached.
Agent control is behind a default-off feature flag. Check first:
sidecar agent list --json
If that answers {"error":{"code":"feature_disabled",...}}, agent control is off. Ask the user to enable it (agent_control under features.flags in ~/.config/sidecar/config.json) rather than turning it on yourself.
The safe sequence
Do these in order. Each step exists because skipping it is how a coordinated agent ends up wedged, duplicated, or typing into the wrong pane.
1. Discover
sidecar shell list --json # what shells exist
sidecar agent list --json # which of them have a live agent, and its status
A target is a Sidecar-managed shell. A bare target first matches an exact tmux session name. An ordinary display name such as rev U3-c or Shell 3 still resolves when unique; ambiguity refuses. A missing sidecar-sh-*, sidecar-ws-* or sidecar-tp-* target never falls back to a display name. name:DISPLAY explicitly selects a unique display name, including a session-shaped one, and session:NAME selects an exact session, including literal names starting with name: or session:. agent start --target SESSION and --exact-target interpret the target as a literal exact identity. Inside a managed shell you may omit the target entirely and the command addresses SIDECAR_SHELL. Outside one, name the target.
agent list reports each live pane once, under the project that owns it, however many registered projects can see its checkout. An explicit target is searched across every project; if the same exact session identity exists in several, the project your own shell belongs to breaks the tie, so a sibling worktree resolves from a managed shell without flags. Outside a managed shell the refusal lists the projects and names the fix: --project NAME (a slug, a path, or a worktree Sidecar created, by path or basename) or --shell NAME. Display-name ambiguity always refuses until --project explicitly narrows the search. Remote commands preserve these selector rules and carry parser guards; older owners refuse before mutation and must be upgraded. The project field of a create shell / create worktree --json result is the value --project accepts.
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.
- 14d ago Changed · +2 lines fe8fc43dbeb8
- 1mo ago Changed · +12 lines · +14 tokens per session 9c9c4d570673
- 1mo ago Changed · +4 lines 89f7bb020444
- 1mo ago First seen · 142 lines · 92 tokens per session scan A 15040ff3e182
coordinate-agents is a skill published in the GitHub repository marcus/sidecar (1,091 stars, last pushed 11d ago), licensed MIT. It adds 106 tokens to every session and 3,028 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
revise-roadmap
Revise an implementation roadmap based on critic feedback.
build-knowledge-base
Build or update a persistent repo knowledge base graph.
research-codebase
Document codebase as-is through comprehensive research.
validate-phase-plan-structural
Per-phase plan structural validation gate - evaluates conformance to the concise vertical-slice phase-plan format.
implement
Execute an approved phase plan with TDD, dependency-aware task fan-out, required evidence, and a strict iteration handoff.
review-comments
Execute a feature-level review-comments cycle — aggregate unaddressed PR comments across every Feature.Repos PR, address or dismiss each one, and emit the standard handoff.