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 agentmods add commands/launch-it-labs/log-reducer/logdumpgit clone --depth 1 https://github.com/launch-it-labs/log-reducerWhat 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 | $0.00000 | $0.00455 |
| Opus 5 | $0.00000 | $0.00228 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
logdump 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.
What it actually says
The user has a log on their clipboard. Dump it to a temp file and reduce it using the filters most relevant to your current debugging context.
Step 1 — Save clipboard to file (do NOT read the file contents):
powershell -command "Get-Clipboard | Set-Content C:\tmp\log.txt"
Step 2 — Call reduce_log with the filters YOU need right now:
reduce_log({ file: "C:\\tmp\\log.txt", tail: 2000 })
Start with just tail — no filters. If the output is small enough, you get it directly.
If it's large, you automatically get an enhanced summary listing unique errors, warnings,
timestamps, and components. Use that summary to plan your next call.
Step 3 — Drill down based on what you see:
After the initial call, narrow with the filters that match your investigation:
- Debugging an error? Use
level: "error"orlevel: "warning" - Looking at a specific component? Use
component: "name" - Searching for a pattern? Use
grep: "pattern" - Narrow time window? Use
time_range: "HH:MM-HH:MM" - Need more context around matches? Use
before: 30orafter: 10 - Context window too noisy? Add
context_level: "warning"to filter low-severity context lines
Example follow-up calls:
reduce_log({ file: "C:\\tmp\\log.txt", tail: 2000, level: "error", limit: 5 })
reduce_log({ file: "C:\\tmp\\log.txt", tail: 2000, time_range: "14:02-14:03", before: 50 })
reduce_log({ file: "C:\\tmp\\log.txt", tail: 2000, level: "error", before: 30, context_level: "warning" })
The raw log must NEVER enter the conversation. Do not read C:\tmp\log.txt with the Read tool. Only the reduce_log output should appear in this conversation.
Show the reduced output to the user.
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 First seen · 41 lines · 0 tokens per session scan A e29f09c40b44
logdump is a command published in the GitHub repository launch-it-labs/log-reducer (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 455 tokens. 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 commands, from other repositories
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
validate-dependencies
Validate all task dependencies for issues.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.