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.
git clone --depth 1 https://github.com/tristanmanchester/sifsWrote 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/agents/tristanmanchester/sifs/sifs-search)<a href="https://agentmods.dev/agents/tristanmanchester/sifs/sifs-search"><img src="https://agentmods.dev/badge/agents/tristanmanchester/sifs/sifs-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/agents/tristanmanchester/sifs/sifs-search"><img src="https://agentmods.dev/badge/agents/tristanmanchester/sifs/sifs-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 | $0.00094 | $0.00739 |
| Opus 5.5 | $0.00038 | $0.00296 |
| Sonnet 5.5 | $0.00019 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
sifs-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use sifs search to find code by describing what it does or by naming a symbol
or identifier:
sifs agent-context --json
sifs search "authentication flow" --source ./my-project
sifs search "save_pretrained" --source ./my-project
sifs search "save model to disk" --source ./my-project --limit 10
sifs search "auth flow" --source ./my-project --mode semantic --encoder hashing
sifs symbol SessionToken --source ./my-project --kind class --json
sifs outline src/auth.py --source ./my-project --kind function --symbols-limit 200 --chunks-limit 100 --json
sifs pack "how auth flow works" --source ./my-project --budget-tokens 6000 --json
Use sifs find-related to discover code similar to a known location. Pass
file_path and line from a prior search result.
sifs find-related src/auth.py 42 --source ./my-project
--source defaults to the current directory when omitted; Git URLs are accepted.
Use --filter-path for repository-relative file filters and --limit for
result bounds.
For repeated work, save a profile:
sifs profile save current --source ./my-project --mode bm25 --offline --json
sifs search "startup handshake" --profile current --json
If sifs is not on $PATH, build this Rust binary and use its absolute path.
Capabilities
- Search local directories and Git URLs with hybrid, semantic, or BM25 ranking.
- Discover related code from a known file and line.
- Inspect indexed symbols, file outlines, file paths, chunks, and context packs.
- Discover the CLI/MCP contract with
sifs agent-context --json. - Save reusable source/search defaults with
sifs profile. - Record local feedback with
sifs feedback create. - Inspect index status, indexed files, and chunk coverage when using the MCP server.
- Refresh the MCP index after files change in a long-running agent session.
- Install this agent file with
sifs agent install --target claude-code --artifact skillor the MCPinit_agentcompatibility tool. - Run benchmarks and embedding diagnostics through the CLI when shell access is available.
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.
- 2mo ago First seen · 64 lines · 94 tokens per session scan A 54bb8b4a022d
sifs-search is an agent published in the GitHub repository tristanmanchester/sifs (2 stars, last pushed 29d ago), licensed MIT. It adds 94 tokens to every session and 739 once invoked, about $0.0004 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.
sifs-search compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sifs-searchtristanmanchester/sifs | Agent | 2 | 29d ago | MIT | A | 94 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | yesterday | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 3d ago | MIT | A | 17 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 20 | 5d ago | MIT | A | 28 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 6d ago | MIT | A | 53 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | yesterday | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |