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/atuljha23/holocron/flakygit clone --depth 1 https://github.com/atuljha23/holocronWrote 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/commands/atuljha23/holocron/flaky)<a href="https://agentmods.dev/commands/atuljha23/holocron/flaky"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/flaky.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00341 |
| Opus 5 | $0.00016 | $0.00170 |
| Sonnet 5 | $0.00006 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
flaky 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 4d 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
/holocron:flaky
Target flake: $ARGUMENTS.
Gather
- The test file(s) matching the target.
- Recent git blame on the test and on the code it exercises (
git log -p -- <file>last 5 commits). - If
--log <path>was supplied, read the log and pull out the failure message / stack. - The test harness config (jest/vitest/pytest/go test flags — concurrency, isolation, retries).
Delegate
Hand off to @qa-engineer to walk the flake-triage tree:
- Timing (sleeps, polling without bound, unawaited promises)
- Order dependence (shared state, side effects from sibling tests)
- Environment (wall-clock, tz, locale, random seed, network, ports)
- Resource contention (temp files, databases, parallel workers)
- External (3rd-party, flaky mock, fixture instability)
For each hypothesis, demand a concrete observation that would confirm it.
Output
- Ranked hypotheses (most likely first)
- The probe to run for each hypothesis (a command or added log line)
- A candidate fix once the root is identified
- A guard: the assertion or test-harness setting that prevents reintroduction
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.
- 4d ago First seen · 36 lines · 32 tokens per session scan A de9b61fdff41
flaky is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 341 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 commands, from other repositories
learn
Learn Claude Code best practices and capture lessons into persistent memory.
insights
Surface patterns from your pro-workflow learnings and session history.
wiki
Build, query, and maintain long-lived knowledge bases. Each wiki = markdown folder + SQLite FTS5 shadow index. Survives sessions, indexes auto-load on SessionStart.
handoff
Generate a structured handoff document that another Claude session (or your future self) can consume immediately to continue where you left off.
commit
Create a well-crafted commit after running pro-workflow quality checks.
skill-optimize
Train a skill's SKILL.md by running a SkillOpt-flavored offline loop over accumulated learn-rule corrections.