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 ychampion/cskill-agents --skill null-hardened-feature-overridesgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/null-hardened-feature-overrides)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/null-hardened-feature-overrides"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/null-hardened-feature-overrides/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/ychampion/cskill-agents/null-hardened-feature-overrides"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/null-hardened-feature-overrides.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 | $0.00032 | $0.00397 |
| Opus 5 | $0.00016 | $0.00198 |
| Sonnet 5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
null-hardened-feature-overrides 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 6d 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.
What it actually says
SKILL: Null-Hardened Feature Overrides
Domain: remote-bridge
Trigger: Apply when remote feature flags or runtime override maps can influence thresholds, but the flag service may return null or malformed values.
Source Pattern: Distilled from reviewed remote override and transport-boundary patterns.
Core Method
Treat remote override values as untrusted input rather than configuration you can index directly. Validate the flag payload type, require finite positive numbers, and fall back to the hardcoded default when the override is null, missing, non-object, or otherwise malformed. Preserve hard opt-outs, such as Infinity for tools that self-bound their output, before consulting the remote override layer.
Key Rules
- Guard the override container itself before indexing into it; null or non-object flag payloads must fall back cleanly.
- Accept only finite positive numbers as overrides; reject zero, negatives,
NaN, and infinities. - Preserve hard opt-out semantics like
Infinitybefore consulting override maps so remote flags cannot re-enable disabled behavior. - Clamp fallback behavior against the declared local default instead of trusting remote values to stay within safe bounds.
Example Application
If a growth experiment can adjust persistence thresholds per tool, validate the experiment payload before using it; malformed data should simply leave getPersistenceThreshold and getPerMessageBudgetLimit on their safe defaults rather than crashing the result-storage path.
Anti-Patterns (What NOT to do)
- Do not assume the flag cache always returns a well-formed object; stale or null payloads are part of the contract.
- Do not let a remote override bypass a local hard opt-out, or tools that intentionally self-bound their output can become circular again.
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.
- 6d ago First seen · 28 lines · 32 tokens per session scan A e69b78045f17
null-hardened-feature-overrides is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 397 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.