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 skills/cosmix/loom/loom-feature-flagsnpx skills add cosmix/loom --skill loom-feature-flagsgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-feature-flags)<a href="https://agentmods.dev/skills/cosmix/loom/loom-feature-flags"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-feature-flags.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.05212 |
| Opus 5 | $0.00012 | $0.02606 |
| Sonnet 5 | $0.00005 | $0.01042 |
| Haiku 4.5 | $0.00002 | $0.00521 |
Grade A, and why
loom-feature-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 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flags
Overview
Runtime control over feature availability without redeploying. The hard parts are not the if check — they are: bucketing correctness (stickiness, monotonicity, cross-service consistency), fail-safe evaluation (an outage of the flag service must not take down the app), experiment validity (exposure logging), and lifecycle/technical-debt (stale flags are the #1 real-world feature-flag problem). Optimize for those.
Flag Taxonomy — Type Drives Lifetime and Ownership
The single most useful classification (from Pete Hodgson / Martin Fowler). Type determines expected lifetime, who owns it, and dynamism. Mixing types under one abstraction is a common mistake.
| Type | Purpose | Lifetime | Changes at runtime? | Owner |
|---|---|---|---|---|
| Release toggle | Ship incomplete/unproven code dark, ramp | Days–weeks (SHORT) | Per deploy/ramp | Dev team |
| Experiment | A/B/multivariate measurement | Length of test | Sticky per user | PM / data science |
| Ops / kill-switch | Disable a subsystem under load/incident | Long-lived | On demand (fast) | Ops / SRE |
| Permission | Entitlements: plan tier, beta cohort | Very long / permanent | Per user/segment | Product / billing |
Consequences:
- Release toggles must be removed once the feature is stable — they are debt with a deadline. Track
createdAt + owner + removal ticket. - Ops toggles are permanent and must be evaluated with zero external calls in the hot path (see Kill Switches).
- Permission toggles are effectively long-lived config; don't route them through the "delete after rollout" cleanup process.
- Don't overload one flag to do two jobs (a release toggle that also gates a paid tier). Split them; they have different lifetimes.
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 Changed · -34 tokens per session ec2aedd1273d
- 5d ago First seen · 331 lines · 58 tokens per session scan A 8130ebf1d810
loom-feature-flags is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 5,212 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…
aws-cloudformation-cloudfront
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…