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 logsgit 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/logs)<a href="https://agentmods.dev/skills/jonny981/claude-tandem/logs"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/logs/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/logs"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/logs.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 | $0.00044 | $0.00317 |
| Opus 5 | $0.00022 | $0.00159 |
| Sonnet 5 | $0.00009 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
logs 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 Logs
Read and display entries from ~/.tandem/logs/tandem.log.
Subcommands
Parse $ARGUMENTS to determine the mode:
- No arguments (or empty): Show the last 20 log entries.
errors: Filter to only[ERROR]and[WARN ]entries, show last 50.- A number (e.g.,
50): Show the last N entries. clear: Ask the user to confirm, then truncate the log file (> ~/.tandem/logs/tandem.log).
Output format
Display the log entries in a code block. Each entry follows this format:
2026-02-12 10:30:45 [INFO ] [session-start] provisioned rules files
After the entries, show:
- Current log level:
TANDEM_LOG_LEVELenv var (default:info) - Tip: "Set
TANDEM_LOG_LEVEL=debugfor verbose output" (if not already debug)
If log file doesn't exist
Report: "No log file found at ~/.tandem/logs/tandem.log. Tandem logs are created on first hook execution."
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 · 32 lines · 44 tokens per session scan A 2dfa2b0f0c4e
logs is a skill published in the GitHub repository jonny981/claude-tandem (6 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 317 once invoked, about $0.0002 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
performance-investigation
MUST USE when investigating or fixing performance issues: slow responses, high memory usage, CPU spikes, throughput degradation, or optimization requests. Enforces measure-first methodology — profile before guessing, baseline before fixing, re-measure after every change. Distinct from systematic-debugging (which…
systematic-debugging
Invoke BEFORE attempting any fix when a bug, test failure, error, warning, unexpected behavior, or performance regression appears. Enforces hypothesis-driven root cause analysis — no fix without evidence. Triggers on: error messages, stack traces, "it's broken", "not working", "bug", test failures, blank/white…
error-recovery
Maintains a project-specific known-issues.md mapping recurring errors to their solutions. Consulted automatically by systematic-debugging before investigation. Saves time by avoiding rediscovery of known problems across sessions. Triggers on: "save this fix", "remember this error", "known issues", or automatically…
verify
Execution verification for CLI/script features — runs commands and captures output for human review. Use after /exec for script changes.
r-audit-slop
AI slop audit. Finds dead code, orphan helpers, noop functions.
r-audit
Use when you want a full codebase audit: dispatches parallel reviewer and QA passes across the tree.