Borrowing it
Nothing to install: this file belongs to seldonframe/reelier. 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/seldonframe/reelier/main/.claude/skills/reelier-slice/SKILL.mdgit clone --depth 1 https://github.com/seldonframe/reelierWrote 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/seldonframe/reelier/reelier-slice)<a href="https://agentmods.dev/skills/seldonframe/reelier/reelier-slice"><img src="https://agentmods.dev/badge/skills/seldonframe/reelier/reelier-slice/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/seldonframe/reelier/reelier-slice"><img src="https://agentmods.dev/badge/skills/seldonframe/reelier/reelier-slice.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 | $0.00054 | $0.01346 |
| Opus 5.5 | $0.00022 | $0.00538 |
| Sonnet 5.5 | $0.00011 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
reelier-slice 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reelier slice loop
The authority ledger punishes reasoning that was not measured. In one session four confident estimates were each refuted by running something: "15 missing fault points" (34), "the transitions exist so this is mostly emission" (half needed new mechanism), "opening this gate unlocks 22 tests" (it cost 22), and "this committed pin is the acceptance criterion" (it was unsatisfiable by any implementation). Every one was caught by a measurement that took under two minutes.
The rule: the plan fixes the sequence of gates, never the outcomes. Measure, then decide.
The loop
Run every step. Do not skip 4 or 9 because the change looks small — both have caught defects in two-line diffs.
- Measure the baseline.
node scripts/baseline-diff.mjs --saveon a quiet machine. - Identify the smallest behaviour gap. One point, one boundary, one invariant.
- Add RED tests — or identify existing committed ones. Then verify they are satisfiable (below).
- Independent RED review (fresh subagents). Non-negotiable; see the lens set.
- Implement the smallest change.
- Focused tests —
--test-name-patternon the affected family. - Compare against baseline —
node scripts/baseline-diff.mjs. - Broader suite —
npm testwhen the change touches shared code or exported surface. - Independent GREEN review.
- Commit only if shippable. A change that adds public surface and greens nothing is not shippable — revert it and record why.
The gate
Pass count must not drop, and the failing set must gain no names. baseline-diff enforces both.
If it fails, the default is to revert and record the measurement, not to argue with it. A reverted slice with a written finding is a good outcome; it is how the housekeeping-permission question was located.
Verify a pin is satisfiable before treating it as a goal
A test that injects at a fault point absent from src/ fails because its injector never fires. It
looks identical to an honest RED pin in a suite run, and no implementation of its subject can turn
it green.
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 First seen · 111 lines · 54 tokens per session scan A 9fcfc54d238a
reelier-slice is a skill published in the GitHub repository seldonframe/reelier (3 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,346 once invoked, about $0.0002 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
code-review
Review a diff against its acceptance criteria in four segments (convention adherence, bug scan, historical-context regressions, test-coverage gaps) as a NON-implementing agent. Findings are sorted by severity, each with file:line + a failure scenario. A planted defect must be caught; a clean diff must not be…
receiving-code-review
Handle review feedback on code with care: understand each point, check it against the real code before changing anything, fix what is right, and push back with reasons on what is wrong. Use when review comments arrive.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
review
Review recent changes - run all validators and report status.
Self-Review
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers when changes are >30 LOC, multi-file, hot-path, prompt-affecting, or genuinely uncertain. Bad asks produce bad answers — this skill forces structured verification questions, not "is this good?".
second-opinion
Generate a fresh-context review snapshot of the current task for a clean-memory AI reviewer (any vendor or a clean session). Use at a milestone that looks complete, or when blocked, uncertain, or facing a risky change, to get an independent second opinion before proceeding; shows a security advisory before exporting…