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/gotempsh/temps/flagsgit clone --depth 1 https://github.com/gotempsh/tempsWhat 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 | $0.01210 |
| Opus 5 | $0.00000 | $0.00605 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
flags 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flags command reference
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
flags (alias: flag)
Manage feature flags (runtime config that changes without a redeploy)
Subcommands:
list(ls) - List feature flagsget- Show a feature flag and its per-environment valuescreate- Create a feature flagupdate- Update a flag definition (default value, description, visibility)set- Set a flag value in one environmentclear- Clear a flag override so the environment inherits the defaultdisable- Kill switch: serve the default in this environment, ignoring any overrideenable- Re-enable a flag in this environment after a kill switchrestore- Restore an archived flagarchive- Archive a flag (callers fall back to their own default)
flags list (alias: ls)
List feature flags
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug or ID | - | No |
-e, --environment <name> |
Show values for this environment | - | No |
--include-archived |
Include archived flags | - | No |
--page <n> |
Page number (default: 1) | - | No |
--page-size <n> |
Items per page (default: 20, max: 100) | - | No |
--json |
Output in JSON format | - | No |
flags get
Show a feature flag and its per-environment values
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug or ID | - | No |
--json |
Output in JSON format | - | No |
flags create
Create a feature flag
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug or ID | - | No |
-t, --type <type> |
Value type: bool, string, number, or json | - | Yes |
-d, --default <value> |
Default value, served when nothing more specific applies | - | Yes |
--description <text> |
What this flag controls | - | No |
--client-visible |
Allow this flag to be exposed to browsers (default: server-only) | - | No |
--json |
Output in JSON format | - | No |
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.
- 2d ago First seen · 144 lines · 0 tokens per session scan A 25c628f0746c
flags is a command published in the GitHub repository gotempsh/temps (700 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,210 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
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
deps-age
Analyze dependency freshness and maintenance activity.
release-prep
Automated release readiness validation.
audit-code
When /audit-code [target] is invoked, immediately execute the following steps to analyze code quality, security, and adherence to project standards.
project
Follow the project management workflow defined in .agents/skills/project/SKILL.md.
taskrunner-add
Add a task to the autonomous queue.