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 agentmods add commands/ehmo/gum/gum-callgit clone --depth 1 https://github.com/ehmo/gumWhat 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 | $0.00000 | $0.00669 |
| Opus 5 | $0.00000 | $0.00334 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
gum-call 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 yesterday.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gum call
Generated from
gum schema --json. Do not edit this page by hand; runmake docs-commands.
gum call is the deterministic CLI entry point for catalog operations. Positional args use key=value, key:=json, and @file forms. The risk flag MUST match the resolved variant's risk_class or the call returns RISK_TOOL_MISMATCH before any upstream request.
Usage
gum call <op_id> --risk=<read|write|destructive> [args...] [flags]
Parent
Arguments
| Name | Help |
|---|---|
op_id |
|
args |
Flags
| Flag | Type | Default | Help |
|---|---|---|---|
--confirmed |
bool |
false | Set the signed-confirmation flag for destructive variants |
--csv |
bool |
false | Render output as CSV |
--fields |
string |
Field mask sent to the upstream API (host control) | |
--json |
bool |
false | Render output as JSON (default when piped) |
--markdown |
bool |
false | Render output as Markdown |
--no-field-mask |
bool |
false | Disable upstream field_mask injection |
-o--output |
string |
Output format: table|json|toon|csv|markdown|raw|value() (default: table on a terminal, json when piped) | |
--page-size |
int |
0 | Page size for paginated reads (host control) |
--page-token |
string |
Page token for paginated reads (host control) | |
--raw |
bool |
false | Return the raw upstream JSON without shaping |
--risk |
string |
Risk path: read|write|destructive (required) | |
--skeleton |
bool |
false | Print a fillable template of the op's request fields and exit (no upstream call) |
--token |
string |
HMAC-SHA256 confirmation token returned by a prior destructive attempt | |
--toon |
bool |
false | Render output as TOON |
--variant-id |
string |
Pin variant_id (default: op's default_variant_id) | |
--yes |
bool |
false | Deprecated: destructive variants require --confirmed --token |
--log-format |
string |
json | Log format: json|text |
--log-level |
string |
info | Log level: debug|info|warn|error (overrides GUM_LOG_LEVEL) |
--profile |
string |
default | Profile name to read/write config under |
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.
- yesterday First seen · 55 lines · 0 tokens per session scan A 12c2658faba5
gum-call is a command published in the GitHub repository ehmo/gum (31 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 669 tokens. 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 2026-08-30.
Other commands, from other repositories
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
autospec.plan
Generate YAML implementation plan from feature specification.
version
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
review
Review current changes for correctness, style, and potential issues.
release-tag
Create and push a version tag after a release PR has been merged.
fix
Auto-fix linting, formatting, and common issues.