Atlas / Skills / aden-hive / Terminal Tools Fs Search

Terminal Tools Fs SearchSAFE

skills/aden-hive/terminal-tools-fs-search

Multi-Agent Harness for Production AI

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.0
Hosts
—
License
Apache-2.0
Stars
11,091
01

Overview

Multi-Agent Harness for Production AI

Read from source at commit e9251a22710aOBSERVED · 2026-10-07
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: hive.terminal-tools-fs-search
description: Use terminal_rg / terminal_glob for all filesystem search — your project tree as well as system configs, /var/log, /etc, archive contents. Teaches the rg vs glob vs terminal_exec("find/ls/du/tree") split, common rg flag combos for code/logs/configs, glob patterns for finding files by name, the rule that mtime/size/type predicate queries drop to terminal_exec("find ..."), and that for tree views or single-file stat info you should just use terminal_exec instead of inventing a tool. Read before reaching for raw shell to grep or find anything.
metadata:
  author: hive
  type: preset-skill
  version: "1.0"
---

# Filesystem search

terminal-tools provides two structured search tools: `terminal_rg` (ripgrep for content) and `terminal_glob` (find files by name/glob). Predicate queries (mtime/size/type) and everything else (tree, stat, du) are just `terminal_exec`.

## When to use what

| Task | Tool |
|---|---|
| Find code/text matching a pattern (project tree or any path) | `terminal_rg` (gitignore-aware; defaults to your session workdir) |
| Find files by name/glob (any path) | `terminal_glob` |
| Find files by mtime/size/type predicate | `terminal_exec("find ...")` (see references/find_predicates.md) |
| List a directory | `terminal_exec("ls -la /path")` |
| Tree view | `terminal_exec("tree -L 2 /path")` |
| Single-path stat | `terminal_exec("stat /path")` |
| Disk usage | `terminal_exec("du -sh /path")` or `terminal_exec("du -h --max-depth=2 /")` |
| Count matching lines in returned results | `terminal_rg(...).total` (check `truncated` before treating it as complete) |

## `terminal_rg` — content search

ripgrep is fast, gitignore-aware, and has a deep flag surface. The structured wrapper exposes common search flags directly; `extra_args` accepts additional flags compatible with JSON output. Output modes such as `--count` and `--files-with-matches` are not compatible with this structured interface; use the CLI when that output is needed.

Quickstart installs and verifies ripgrep. Existing installations can be repaired with `uv run scripts/ensure_ripgrep.py --install` from the repository root. The runtime also checks Windows package-manager locations and current registry PATH entries; `HIVE_RIPGREP_PATH` can select an absolute executable path. Startup logs report the executable and version, or instructions to fix the missing dependency.

If ripgrep is unavailable, `terminal_rg` returns `code="ripgrep_required"` without searching by default. For an approximate search, explicitly set `allow_fallback=True`: this uses Python regex, a limited filetype table, and basename globs, and does **not** honor `.gitignore`. Even with opt-in, context, `extra_args`, unknown filetypes and complex globs require ripgrep and return an error. Inspect `fallback_limitations`; do not treat approximate results as a gitignore-aware inventory.

With `context=N`, surrounding lines are returned in `context`, separate from `matches`. Both contain `path`, `line`, and `text`; `total` counts only match entries.

### Common patterns

```
# All Python files containing "TODO"
terminal_rg(pattern="TODO", path=".", type_filter="py")

# Case-insensitive, with context
terminal_rg(pattern="error", path="/var/log", ignore_case=True, context=2)

# Search hidden files (rg ignores them by default)
terminal_rg(pattern="api_key", path="~", hidden=True)

# Don't respect .gitignore (find files git would ignore)
terminal_rg(pattern="generated", path=".", no_ignore=True)

# Multi-line pattern (e.g., function definitions spanning lines)
terminal_rg(pattern=r"def\s+\w+\(.*\n.*\n", path="src", extra_args=["--multiline"])

# Specific filename glob
terminal_rg(pattern="version", path=".", glob="*.toml")
```

### rg flag idioms

| Flag | Effect |
|---|---|
| `-tpy` (`type_filter="py"`) | Only Python files |
| `-uu` | Don't respect any ignores (incl. `.git/`) |
| `--multiline` (`extra_args`) | Allow regex spanning lines |
| `--max-count` (`max_count`) | Stop after N matches per file |
| `--max-depth` (`max_depth`) | Limit recursion |
| `-w` (`extra_args`) | Whole word match |
| `-F` (`extra_args`) | Fixed string (no regex) |

See `references/ripgrep_cheatsheet.md` for the long form.

## `terminal_glob` — find files by name

Lists files matching a glob, gitignore-aware (backed by `rg --files`). The pattern is widened for you so a bare stem Just Works — the actual glob run is returned as `expanded_pattern`:

- `lk_scan_post_reactors` → matched as `**/*lk_scan_post_reactors*` (recursive substring)
- `*.py` → matched as `**/*.py` (recursive by default)
- `src/**/*.py` → used verbatim

If `rg` is unavailable, filename search retains a best-effort walk with `fallback="python-walk"` and a note that `.gitignore` is not honored.

```
# Find a file by stem anywhere under a tree
terminal_glob(pattern="lk_scan_post_reactors", path="core/framework/skills")

# All YAML configs under /etc
terminal_glob(pattern="*.yaml", path="/etc")

# Include .gitignored / hidden / build-cache files
terminal_glob(pattern="*.log", path=".", include_ignored=True)
```

For **predicate** queries (modified in last N days, larger than N MB, only dirs/symlinks), `terminal_glob` is the wrong tool — drop to `terminal_exec("find ...")`. See `references/find_predicates.md`.

## Output truncation

Both tools return `truncated: true` when output exceeded the inline cap. For `terminal_rg`, matches were dropped (refine the pattern or narrow the path); for `terminal_glob`, results past `max_results` (default 1000) were dropped — the search stops early at the cap, so narrow the pattern rather than raising it. `terminal_glob` also returns `timed_out: true` (with the partial results it gathered) when the walk exceeded its deadline.

## Anti-patterns

- **`terminal_rg` is the project search tool** — gitignore-aware and returns structured matches; use it for in-project search as well as raw paths.
- **Don't reach for `terminal_glob` to list one di
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWInventory / provenance · inv.symlink · CWE-1104
CLAUDE.md
CLAUDE.md
Why it matters. link not followed

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha e9251a22710afull audit observations/trust-audit/skill/aden-hive__terminal-tools-fs-search.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-07e9251a22710aSAFEB89first audit
05

Questions

What does the Terminal Tools Fs Search skill do?

Multi-Agent Harness for Production AI

Is Terminal Tools Fs Search safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Terminal Tools Fs Search access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (e9251a22710a), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement