Borrowing it
Nothing to install: this file belongs to timfewi/tentaflake. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/timfewi/tentaflake/main/.agents/skills/tentaflake-change-review/SKILL.mdgit clone --depth 1 https://github.com/timfewi/tentaflakeWrote 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/timfewi/tentaflake/tentaflake-change-review)<a href="https://agentmods.dev/skills/timfewi/tentaflake/tentaflake-change-review"><img src="https://agentmods.dev/badge/skills/timfewi/tentaflake/tentaflake-change-review/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/timfewi/tentaflake/tentaflake-change-review"><img src="https://agentmods.dev/badge/skills/timfewi/tentaflake/tentaflake-change-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 81 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00056 | $0.01808 |
| Opus 5 | $0.00028 | $0.00904 |
| Sonnet 5 | $0.00011 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
tentaflake-change-review 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 12d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tentaflake — Change Review
Overview
A deliberately small verification discipline for changes to the tentaflake template. It borrows one idea from heavyweight AI-engineering frameworks — traceability: every change ties back to a reason and forward to a check — but strips the ceremony (no ISO matrices, no multi-cycle lifecycle, no red-team gates). It is sized for a ~30-file NixOS template maintained by Conventional Commits + PRs.
The goal: stop "orphaned" changes (code with no stated reason), silent assumptions, and doc drift — without slowing ordinary work.
When to use
- Planning any non-trivial change (new module, option, lib arg, script, CI step).
- Implementing a bug fix or feature.
- Reviewing a diff before opening or merging a PR.
Skip it for pure formatting, typo fixes, or comment-only edits.
The three gates
Every change must clear three gates before it is "done". State them explicitly in your plan and in the PR description.
1. REASON — why does this change exist?
Link the change to one of:
- an existing GitHub issue (
gh issue view <n>), - a bug reproduced with a concrete command/output, or
- a one-sentence requirement written before the code.
If you cannot name the reason, do not write the code. A change whose only justification is "seemed nice" is an orphan — either write the requirement first or drop it.
Anti-pattern: adding a
tentaflake.*option "just in case". Options are API surface; each one needs a stated need and a default that keeps existing configs working.
2. VERIFY — how do we know it works?
Name the check before implementing, and actually run it. Pick the tightest applicable command from the repo's real toolchain:
| Change touches | Verification |
|---|---|
Any .nix (module/lib/config) |
nix flake check |
| Host config / new option | nix build .#nixosConfigurations.tentaflake.config.system.build.toplevel --no-link (the attr follows constants.hostName) |
| Runtime behavior (unit, state dir, CLI) | nix build .#checks.x86_64-linux.vm-integration -L |
| Container image pin | nix build .#checks.x86_64-linux.image-pinning |
| Formatting | nix fmt (CI runs nix fmt -- --ci) |
| Rust workspace | cargo fmt --all -- --check, cargo clippy --workspace --all-targets -- -D warnings, and cargo test --workspace |
| Shell scripts | shellcheck installer/*.sh scripts/*.sh |
| Installer-generated flake | ./scripts/generated-flake-test.sh |
| ISO changes | nix build .#installer-iso |
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.
- 12d ago First seen · 171 lines · 56 tokens per session scan A 911273329d98
tentaflake-change-review is a skill published in the GitHub repository timfewi/tentaflake (30 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,808 once invoked, about $0.0003 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
find-security-vulnerabilities-in-code
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy…
fix-security-vulnerabilities-with-strix
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use…
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
analyzing-linux-elf-malware
Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…