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 mxyhi/ok-skills --skill orca-replaygit clone --depth 1 https://github.com/mxyhi/ok-skillsWrote 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/mxyhi/ok-skills/orca-replay)<a href="https://agentmods.dev/skills/mxyhi/ok-skills/orca-replay"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/orca-replay/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/mxyhi/ok-skills/orca-replay"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/orca-replay.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 | $0.00067 | $0.01667 |
| Opus 5.5 | $0.00027 | $0.00667 |
| Sonnet 5.5 | $0.00013 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
orca-replay 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading a Recorded Agent Run
A recording is evidence. Your memory of a session is not, and neither is a transcript you were handed — both are missing the tool results, the exit codes, and the files that changed without anyone mentioning them.
The rule: when a question is about something that already happened, read the trace before you answer. Do not reconstruct it. If a recording exists, guessing is the wrong move even when the guess would have been right.
This skill does not drive the agent — it reads what an earlier one did. Pair it with whatever
harness produced the run: Claude Code, Codex, opencode, Cursor, or a framework agent recorded with
orca record generic-openai -- <cmd>.
When to use
- "Why did you delete / overwrite / move X?"
- "What changed this file?" or "Which step broke the build?"
- "Can you reproduce yesterday's failure?"
- "Would a different model have got this right?"
If the user wants to start recording rather than read a past run, that is orca record <agent>,
not this skill.
Setup check
node --version # require Node 20+
which orca || npm install -g orcareplay
orca list # at least one run, or there is nothing to read
Workflow
1. Find the run
orca_list_runs — newest first, and it names the run each fork came from. Skip it only when the
user clearly means the most recent one; every other tool defaults to run: "last".
2. Narrow to the chain that produced the thing being asked about
orca_show_run gives the whole timeline: model turns with token counts and stop reasons, tool
calls with arguments and results, shell commands with exit codes, and every file the run changed.
Good for orientation, long for a specific question.
orca_graph is usually the better tool. It returns causal edges — which event produced which. Pass
to: <event seq> to get only the chain that produced one event. That is the shape of an answer
to "why did this happen"; the full timeline is the shape of an answer to "what happened".
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 · 140 lines · 67 tokens per session scan A 94d64489ed45
orca-replay is a skill published in the GitHub repository mxyhi/ok-skills (500 stars, last pushed 2d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,667 once invoked, about $0.0003 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 2026-10-19.
Other skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
debugging-and-error-recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
diagnosing-superpowers
A diagnostic workflow for investigating problems in Superpowers agent sessions using saved conversation records. It requires evidence linked to exact file paths and line numbers, then organizes findings into a report.
debugging-and-error-recovery
A systematic debugging procedure for finding the underlying cause of failed tests, broken builds, bugs, and unexpected behavior. It emphasizes reproducing the problem, preserving evidence, fixing the cause, and checking the fix.