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-patternsnpx skills add kelp/agent-plugins --skill tiger-patternsgit 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 | $0.00067 | $0.00854 |
| Opus 5 | $0.00034 | $0.00427 |
| Sonnet 5 | $0.00013 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
tiger-patterns 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tiger Style -- Quick Reference
This project follows TigerBeetle's Tiger Style. For full
rationale and worked examples, read
${CLAUDE_PLUGIN_ROOT}/docs/TIGER_STYLE_REFERENCE.md.
Safety
Assertions -- minimum two per function on average. Assert arguments, return values, pre/postconditions, invariants. Pair assertions across code paths. Assert positive space (what you expect) AND negative space (what you don't). Split compound asserts:
// WRONG
assert(a and b);
// RIGHT
assert(a);
assert(b);
Bounded loops, no recursion -- every loop has an upper bound; convert recursive algorithms to iterative. For genuinely non-terminating loops, assert:
while (true) {
assert(self.running);
// ...
}
Static memory -- allocate everything at init from a sized arena. After init, the allocator is read-only.
Errors -- handle every one. catch {} requires a
comment explaining why dropping is safe. Brace
multi-line if bodies.
Naming
snake_casefor fn / var / file. PascalCase for types.- No abbreviations (except
i,j,kfor sort/matrix indices). - Acronyms keep caps:
VSRState, notVsrState. - Units as suffixes, descending significance:
latency_ms_max,bytes_per_sector. - Helper called by one fn: prefix with caller name:
read_sector_callback(). - Callbacks go last in parameter lists.
- Use
options: structwhen args could be mixed up:
pub fn open(path: []const u8, options: struct {
read: bool = true,
write: bool = false,
}) !File { ... }
Function Shape
- Hard limit: 70 lines per function.
- Inverse hourglass: few params, simple return, meaty middle.
- Centralize control flow -- don't duplicate branching in helpers.
- Push
ifs up, pushfors down.
Variables and Aliasing
- Smallest possible scope.
- Minimize variables in scope.
- Don't take aliases to variables.
- Args > 16 bytes that shouldn't copy: pass
*const T. - Group alloc +
deferwith surrounding newlines.
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 · 125 lines · 67 tokens per session scan A 7515df724bb4
tiger-patterns is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 67 tokens to every session and 854 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 2026-08-31.
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).