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 skills add Morningstar202604/awesome-skillkit --skill feature-flags-architectgit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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/morningstar202604/awesome-skillkit/feature-flags-architect)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/feature-flags-architect"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/feature-flags-architect/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/skills/morningstar202604/awesome-skillkit/feature-flags-architect"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/feature-flags-architect.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 | $0.00141 | $0.03184 |
| Opus 5.5 | $0.00056 | $0.01274 |
| Sonnet 5.5 | $0.00028 | $0.00637 |
| Haiku 4.5 | $0.00014 | $0.00318 |
Grade A, and why
feature-flags-architect 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 1mo 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flags Architect
The discipline of feature flags across their full lifecycle: classify, ship, ramp, retire. Most teams treat a flag as a throwaway if statement; this skill treats it as a controlled lifecycle with measurable debt.
Input Checklist
| Input | Required | Description |
|---|---|---|
| Target repo path | No | --repo, defaults to the current directory .; used for code scanning and git introduction-time detection |
| Flag documentation path | No | For the kill-switch audit, --flag-doc, e.g. docs/feature-flags.md; if omitted, only a code-side scan is performed |
| Flag aging parameters | No | flag_debt_scanner's --max-age-days (default 90), --min-uses |
| Rollout parameters | No | rollout_planner's --population --target-percent --duration-days --strategy |
| Output format | No | --format text|json; CI uses json |
When something is missing, ask for it all at once:
"Please provide: (1) target repo path (default .); (2) flag documentation path (needed for the kill-switch audit, e.g. docs/feature-flags.md; skip if none); (3) population size / target percentage / duration (for rollout); (4) debt half-life --max-age-days (default 90). I'll use defaults for everything else; once confirmed, I'll start."
Pre-flight Checks
- Python 3.8+ is available:
python3 --version→ prints a version number (e.g.Python 3.11.0). Ifcommand not foundor the version is <3.8 → prompt to install, then STOP. - The three scripts are on disk:
test -f scripts/flag_debt_scanner.py && test -f scripts/rollout_planner.py && test -f scripts/kill_switch_audit.py→ all exist; if any is missing → STOP and report the specific filename. - git is available (used to locate when a flag was introduced): run
git rev-parse --is-inside-work-treeinside--repo→ outputstrue. If it is not a git repo, the debt scanner's "introduction time" criterion degrades to file mtime, and the user must be told about this degradation.
Core Principle: a Flag Is a Lifecycle, Not an if
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/flag_request_template.md 1.7 KB
- references/flag_lifecycle.md 5.7 KB
- references/flag_taxonomy.md 4.4 KB
- references/provider_comparison.md 5.0 KB
- references/rollout_strategies.md 4.9 KB
- scripts/flag_debt_scanner.py 4.7 KB runs code
- scripts/kill_switch_audit.py 4.9 KB runs code
- scripts/rollout_planner.py 4.4 KB runs code
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.
- 1mo ago Changed · -6 tokens per session 9d9f217a15fd
- 1mo ago Changed · -9 lines · +26 tokens per session 54f50aade3a0
- 1mo ago First seen · 224 lines · 121 tokens per session scan A f403072703a5
feature-flags-architect is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 141 tokens to every session and 3,184 once invoked, about $0.0006 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.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.