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 pktikkani/agent-skills --skill optimize-p95git clone --depth 1 https://github.com/pktikkani/agent-skillsWrote 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/pktikkani/agent-skills/optimize-p95)<a href="https://agentmods.dev/skills/pktikkani/agent-skills/optimize-p95"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/optimize-p95/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/pktikkani/agent-skills/optimize-p95"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/optimize-p95.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 | $0.00050 | $0.00799 |
| Opus 5 | $0.00025 | $0.00400 |
| Sonnet 5 | $0.00010 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
optimize-p95 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize p95 (dynamic workflow)
Goal: hit the user's stated latency target (default: p95 < 300ms) with measured proof.
-
Confirm the target metric and the benchmark command that reports p95. If no benchmark exists, create a minimal reproducible one first — the loop cannot self-verify without it.
-
Detect the stack from repo markers before picking tools — do not assume:
pyproject.toml/requirements.txt→ Python: profile with py-spy (fallback cProfile), benchmark with pytest-benchmark or hyperfine.package.json→ Node/TS: profile with clinic flame or 0x (fallbacknode --cpu-prof), benchmark with autocannon (HTTP) or hyperfine.go.mod→ Go: pprof (go test -cpuprofileor net/http/pprof), benchmark withgo test -benchor vegeta (HTTP).Cargo.toml→ Rust: cargo flamegraph, benchmark with criterion or hyperfine.- Mixed repo: profile the service the p95 target refers to; ask if ambiguous. Install the chosen profiler if missing; verify it runs before starting the loop.
-
Launch a dynamic workflow (use "ultracode" if needed) with this loop: profile → identify top hotspot → apply one fix → re-run benchmark → compare p95 → repeat until target met. Don't stop until the benchmark confirms the target.
Role hierarchy (optional — assumes a multi-agent setup with subagents and an external Codex CLI; on a single-agent setup run the loop yourself):
- Fable (this session) = chief architect. Owns the loop, reads profiler output, decides which hotspot to attack and when the target is met. Does not write the fixes itself.
- Codex = solution architect. For each hotspot, Fable consults Codex
(
codex exec) for the fix design; Fable reconciles it with its own plan and issues one agreed instruction. - Opus subagents = developers. Spawn with
model: opus; they implement exactly the agreed instruction in their own worktree — no improvising beyond it.
-
Each candidate fix runs in its own Opus subagent/worktree; the chief architect keeps only changes that measurably improve p95.
-
Report: before/after p95, list of changes kept, profiler evidence. Write the full log to a file; reply with the path + final numbers only.
Constraints: cap token usage if the user gives a budget; simplest fix first per design-best-practices; no speculative micro-optimizations.
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.
- 8d ago First seen · 62 lines · 50 tokens per session scan A 39aa64050914
optimize-p95 is a skill published in the GitHub repository pktikkani/agent-skills (2 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 799 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…