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 agentmods add skills/kelp/agent-plugins/tiger-checknpx skills add kelp/agent-plugins --skill tiger-checkgit clone --depth 1 https://github.com/kelp/agent-pluginsWhat 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 | $0.00044 | $0.01426 |
| Opus 5 | $0.00022 | $0.00713 |
| Sonnet 5 | $0.00009 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
tiger-check 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 2d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tiger-check [file]
Audit Zig source files for mechanical Tiger Style
violations. If a file path is given, check that file.
Otherwise check all *.zig files that were modified in
the current git diff (staged and unstaged).
Only mechanical rules are covered, checked by reading the
file rather than by a parser -- the function-length and
compound-assertion checks approximate brace and expression
matching, so treat their output as a strong signal, not a
guarantee. Subjective rules (naming quality, prose,
"simplicity") are not. For those, lean on the patterns
in ${CLAUDE_PLUGIN_ROOT}/docs/TIGER_STYLE_REFERENCE.md.
Procedure
1. Determine target files
If argument provided:
- Check only that file.
If no argument:
- Run
git diff --name-onlyandgit diff --cached --name-only. - Filter to
*.zigfiles (include any path, not justsrc/*.zig). - If no modified Zig files, report "No modified Zig files to check" and exit.
2. Read each target file
Use the Read tool to read the full contents.
3. Check for violations
Apply each check below to each file. Report every violation with file path, line number (or line range for function-length), and a one-line fix suggestion.
Check 1: Function length > 70 lines
For each function definition (fn name(...) or
pub fn name(...)), find the matching closing } for
its opening { by reading the file and tracking brace
depth (this is an approximation, not a parse -- watch for
braces inside string literals and comments). If the body
spans more than 70 lines (closing line minus opening line
70), flag it.
Report: WARN: <start>-<end>: function '<name>' is <N> lines (limit 70).
Fix: "Split into helper functions. Push fors down
into helpers; keep branching in the parent."
Check 2: Line length > 100 columns
For each line whose character length exceeds 100, flag it.
Caveats:
- Skip lines that are entirely a single string literal
(e.g. a long URL in a comment or
const), since wrapping would change semantics. Flag with a note rather than as a violation.
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.
- 2d ago First seen · 199 lines · 44 tokens per session scan A f07c0e4936b7
tiger-check is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 1,426 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 2026-08-31.
Other skills, from other repositories
strategy-red-team
Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy…
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
competitive-battlecard
Create sales-ready competitive battlecards comparing your product against a specific competitor — positioning, feature comparison, objection handling, and win/loss patterns. Use when preparing sales teams, creating competitive materials, or responding to 'why not competitor X?'.
stakeholder-map
Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.
ms
Skill "ms" from boshu2/agentops, covering ms — metaskill search/load engine, constraints, quick start, consume — mcp-primary (mcpms) and write / admin — cli-only (verified landing in the live db).