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 christopherkarani/ryk --skill ryk-replaygit clone --depth 1 https://github.com/christopherkarani/rykWrote 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/christopherkarani/ryk/ryk-replay)<a href="https://agentmods.dev/skills/christopherkarani/ryk/ryk-replay"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/ryk-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/christopherkarani/ryk/ryk-replay"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/ryk-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 | $0.00000 | $0.00283 |
| Opus 5 | $0.00000 | $0.00142 |
| Sonnet 5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
ryk-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 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.
This is a copy
91% identical to replay — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
ryk-replay
Show and explain the latest ryk session replay.
When to use
Use this skill after running an ryk-protected session to review what happened, verify the audit log, and check for any policy violations or redactions.
Commands
Replay the most recent session:
ryk replay --session last
Replay with hash-chain verification:
ryk replay --session last --verify
For machine-readable output:
ryk replay --session last --json
No session found
If no session exists, you will see an error like:
No sessions found in .ryk/sessions/
To create a session, run a command through ryk first:
ryk run -- echo hello
Then retry the replay command.
What replay shows
- Session events (commands, file operations, network requests)
- Policy decisions (allow, block, ask, warn)
- Redacted fields (secrets removed before logging)
- Hash-chain verification status (tamper-evident audit)
Notes
- This skill does not modify host configuration.
- The plugin does not collect telemetry. Machine-readable replay calls are excluded from release CLI telemetry; see
docs/telemetry.md. - Replay reads local audit logs only; no external service is contacted.
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 · 57 lines · 0 tokens per session scan A 522b07b33de1
ryk-replay is a skill published in the GitHub repository christopherkarani/ryk (39 stars, last pushed 19d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 283 tokens. A static security scan graded it A with 0 findings. It is 91% identical to replay, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
debug-triage
Use when triaging a pasted error, stack trace, or terminal transcript. Activates on "debug this", "fix this", "why is this broken", or when a user pastes red terminal output. Produces a tight cause-fix-test report, not a lecture.
systematic-debug
A structured debugging workflow that moves from observing an error to reproducing it, testing possible causes, fixing it, and preventing regression.
hypothesis-debug
A structured method for debugging failures by comparing multiple possible causes and testing which ones the evidence rules out. It examines code, the environment, data, and measurement errors.
build-fix
A step-by-step process for fixing build and type-checking errors in projects such as TypeScript, Java, Python, or Rust.
systematic-debugging
Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.