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 jonny981/claude-tandem --skill sessionsgit clone --depth 1 https://github.com/jonny981/claude-tandemWrote 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/jonny981/claude-tandem/sessions)<a href="https://agentmods.dev/skills/jonny981/claude-tandem/sessions"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/sessions/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/jonny981/claude-tandem/sessions"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/sessions.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 | $0.00029 | $0.00451 |
| Opus 5 | $0.00015 | $0.00226 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
sessions 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 9d 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
Tandem Sessions
Inspect the session registry at ~/.tandem/sessions/.
Steps
-
List all session directories under
~/.tandem/sessions/. For each, readstate.jsonand display:- Session ID
- Project (basename of project path)
- Branch
- Status (active/ended)
- Current task
- Last heartbeat (and how long ago)
- PID (and whether it's still alive:
kill -0 $pid)
-
Group by project to show topology: which sessions share a project.
-
Identify orphans: sessions where the PID is dead or heartbeat is older than 5 minutes with a dead process. Offer to clean them up (delete the session directory) if found.
Output format
Active Sessions:
jonnyn-cv (2 sessions)
abc123 main "building session topology" heartbeat: 30s ago pid: 12345 ✓
def456 main "fixing CSS layout" heartbeat: 2m ago pid: 12346 ✓
claude-tandem (1 session)
ghi789 main "adding frontmatter schema" heartbeat: 1m ago pid: 12347 ✓
Orphaned Sessions:
jkl012 jonnyn-cv pid: 99999 ✗ (dead) last heartbeat: 15m ago
→ Clean up? (delete ~/.tandem/sessions/jkl012/)
Arguments
- No arguments: show all sessions
clean: force-clean all orphaned sessions without prompting<session-id>: show detailed state.json for a specific session
Implementation
Use bash to read ~/.tandem/sessions/*/state.json files. Check PIDs with kill -0. Calculate heartbeat age from the ISO timestamp. No external dependencies beyond jq.
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.
- 9d ago First seen · 49 lines · 29 tokens per session scan A 3648c6d6e833
sessions is a skill published in the GitHub repository jonny981/claude-tandem (6 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 451 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
r-init
Use to initialize RDF governance on a new or existing repository.
r-build
Use when a plan exists and you want it built: dispatches the plan-execution orchestrator (engineer/QA/review gates) per phase at the right tier.
r-refresh
Use when the codebase has drifted from its governance docs and you want them re-derived from source.
r-save
Use at the end of a session to sync state — plan progress, memory, and the session log.
r-start
Use at the start of a session to reload project context and show current health, pipeline position, and open work.
r-util-proj-cross
Cross-project analysis for workspace project sets. Reads MEMORY.md, PLAN.md.