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 AleksandarBisevac/claude-plugins --skill before-you-claimgit clone --depth 1 https://github.com/AleksandarBisevac/claude-pluginsWrote 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/aleksandarbisevac/claude-plugins/before-you-claim)<a href="https://agentmods.dev/skills/aleksandarbisevac/claude-plugins/before-you-claim"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/before-you-claim/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/aleksandarbisevac/claude-plugins/before-you-claim"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/before-you-claim.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 | $0.00276 | $0.02084 |
| Opus 5.5 | $0.00110 | $0.00834 |
| Sonnet 5.5 | $0.00055 | $0.00417 |
| Haiku 4.5 | $0.00028 | $0.00208 |
Grade A, and why
before-you-claim 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 26d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before you claim
Every defect class below was written by an agent that had read the rules and was following
them; the moment of writing had no question. This skill is the question — seven of them, each
answered with something that can be shown. It holds no rule of its own: no-silent-pass,
writing-python and CLAUDE.md say how; this asks did you, on this change, and where is the
evidence?
Questions 1, 2, 5 and 7 are one line each because the evals said so. Run against a baseline
with no skill on 2026-09-12, twice and on two models, the arms tied on those four at full marks
and separated on question 4 both times. They still get asked; they no longer get a paragraph.
The runs and their grading are in ../before-you-claim-workspace/iteration-4/benchmark.json.
Two touches
Before the first edit, one line: which questions this change will have to answer
(touches: 1, 3, 4). The sweep, the mutation and the second measurement are cheap before the
edit and expensive after; naming the question is what gets them done while they are cheap.
Before you say done, the claims: block (shape at the end) — one line per question, each
carrying the evidence you gathered or n/a — <reason>. It ends whatever leaves your hands: the
commit message when you commit; otherwise your notes, the PR description, or the message back
to the orchestrator. There is no "done except the block". A line that asserts where evidence
should be ("yes, it fails", no red output shown) is the skill not being used.
The hook that asks for the block sees git commit only after &&, after ;, or at the start
of the command — not one that begins its own line under a heredoc, and not -F -. Its silence
is not a verdict.
The seven questions
1. What does this sentence claim the code does — and where is the line that does it? The
file:line, or the sentence rewritten to say only what the code does.
scripts/claim-lines.py <diff> --tree <checkout> lists the added prose that claims behaviour.
What ships with it
3 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.
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.
- 26d ago First seen · 119 lines · 276 tokens per session scan A 3dd382de5f1b
before-you-claim is a skill published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 276 tokens to every session and 2,084 once invoked, about $0.0011 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 2026-09-18.
Other skills, from other repositories
proof-audit
Audit test suite health — find flaky tests, slow tests, coverage gaps, and testing anti-patterns. Use when asked to "audit tests", "fix flaky tests", "why are tests slow", "test health", or "improve test suite".
g-review
Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.
g-refactor
Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.
g-audit
Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.
rust-intel
Hard rules for writing Rust in code that already compiles and passes tests but is silently broken, slow, or semver-fragile. Load this BEFORE writing any Rust code. Targets bugs that survive rustc, clippy, and cargo test but fail in production or rot the codebase. Covers async, unsafe, FFI, concurrency, crypto…
rust-intel
Hard rules for writing Rust in code that already compiles and passes tests but is silently broken, slow, or semver-fragile. Load this BEFORE writing any Rust code. Targets bugs that survive rustc, clippy, and cargo test but fail in production or rot the codebase. Covers async, unsafe, FFI, concurrency, crypto…