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 Enakoneschniy/claude-dev-stack --skill cds-searchgit clone --depth 1 https://github.com/Enakoneschniy/claude-dev-stackWrote 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/enakoneschniy/claude-dev-stack/cds-search)<a href="https://agentmods.dev/skills/enakoneschniy/claude-dev-stack/cds-search"><img src="https://agentmods.dev/badge/skills/enakoneschniy/claude-dev-stack/cds-search/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/enakoneschniy/claude-dev-stack/cds-search"><img src="https://agentmods.dev/badge/skills/enakoneschniy/claude-dev-stack/cds-search.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 | $0.00027 | $0.00360 |
| Opus 5.5 | $0.00011 | $0.00144 |
| Sonnet 5.5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
cds-search 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 1mo 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
/cds-search -- Search session memory
Search for past decisions, bugs, patterns, and observations stored in the project's SQLite session database.
How to execute
-
Extract the search query from
$ARGUMENTS(everything after/cds-search). -
Primary path (MCP tool): Call
mcp__cds__sessions.searchwith the query:mcp__cds__sessions.search({ query: "$ARGUMENTS" })Format the returned hits as a readable list showing:
- Observation type (decision, bug, pattern, etc.)
- Content snippet (first 2-3 lines)
- Session date
- Session ID (abbreviated)
-
Fallback path (CLI): If
mcp__cds__sessions.searchis not available (MCP server not registered), use Bash:Bash("npx claude-dev-stack search \"$ARGUMENTS\"")Display the CLI output verbatim.
When to use
- User asks about past decisions ("what did we decide about X")
- User asks about past bugs ("did we see this bug before")
- User asks about patterns ("how did we implement X")
- User explicitly invokes
/cds-search
Notes
- Results are ranked by FTS5 BM25 relevance
- Only searches the current project's sessions.db
- For cross-project search, use the CLI directly on each project
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.
- 1mo ago First seen · 49 lines · 27 tokens per session scan A 986043501688
cds-search is a skill published in the GitHub repository Enakoneschniy/claude-dev-stack (5 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 360 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 2026-08-31.
Other skills, from other repositories
context-manager
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.
knowledge-ops
Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or governed Agent/Wiki promotion.
session-learn
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
ensemble-sessionlog
Save a structured session transcript to SessionLogs with key decisions, commands, and resolutions (Codex skill for /ensemble:sessionlog).
guard
Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous…
obsidian-untangle-knot
Offload an Obsidian hub note that too many notes link to (an in-degree tangle). The main signal of a tangle is a high in-degree (tens to hundreds of incoming links); out-degree is secondary. The skill creates sub-MOCs under the hub's existing categories and redirects incoming links from resource notes to the specific…