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 sjarmak/coding-agent-workflows --skill search-sessionsgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/search-sessions)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/search-sessions"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/search-sessions/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/sjarmak/coding-agent-workflows/search-sessions"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/search-sessions.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 | $0.00023 | $0.00401 |
| Opus 5.5 | $0.00009 | $0.00160 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
search-sessions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/search-sessions — Search past agent sessions
Use an installed city-search command or an equivalent local transcript index. Confirm the CLI with city-search --help; this skill does not install or rebuild it. Search is a disposable projection,
not current authority: verify historical claims against the canonical work
record or destination before acting. Transcript content stays local.
Preflight
city-search health --json
Check updated_at and parse_errors before interpreting absent results.
Missing or stale coverage is not evidence that a conversation never happened.
Report a failed read; do not rebuild shared state or run CASS repair commands.
The configured index owner controls refreshes; preserve original transcript sources.
Find relevant sessions
Current workspace and recent matches:
city-search sessions --workspace "$(pwd)" --json --limit 5
Direct search:
city-search search "error message or subsystem" --json --limit 5
Inspect a hit
Search emits one metadata object per line. Use its exact source, line, and
digest for a preserved citation, even if the original file changed or vanished:
city-search view '<source>' -n <line> --digest '<digest>' --json
city-search expand '<source>' -n <line> --digest '<digest>' -C 3 --json
If expected history is missing
city-search health --json
Tips
- Start with an exact error string, workspace path, or subsystem name.
- Search accepts exact
--provider,--workspace, and--sessionfilters. - Inspect only the strongest hits; do not export transcript text to analytics.
- Check prior sessions before re-debugging an unfamiliar failure.
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.
- 18d ago First seen · 59 lines · 23 tokens per session scan A dec66b0df606
search-sessions is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 401 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
orca-replay
Answer questions about an earlier agent run from its recording rather than from memory, and replay or fork that run. Use when the user asks why a previous run did something, which step changed a file or broke the build, whether yesterday's failure still reproduces, or whether a different model would have got it right.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
doris-debug-resource-isolation
Use for Doris Workload Group / resource tag queue starvation, CPU/memory isolation leaks, and workload policy debugging. Commands: SHOW WORKLOAD GROUPS, EXPLAIN resource.
mm-doctor
A diagnostic workflow for checking the health of the mm system, including its configuration, project links, note vault, passports, session archive, and planning consistency.
booster-cognitive-runtime
A set of tools that helps a coding agent understand a repository before changing it and check the result afterward. It uses code structure, Git history, project memory, diagnostics, and validation checks.