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 abhisekjha/pith --skill pith-archgit clone --depth 1 https://github.com/abhisekjha/pithWrote 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/abhisekjha/pith/pith-arch)<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-arch"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-arch/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/abhisekjha/pith/pith-arch"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-arch.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 | $0.00040 | $0.00437 |
| Opus 5 | $0.00020 | $0.00218 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
pith-arch 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 9d 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.
What it actually says
Architecture decision format. Structured. No narrative.
Decision: [what is being decided — one line]
| Option | Pro | Con | Complexity |
|---|---|---|---|
| A | ... | ... | low/med/high |
| B | ... | ... | low/med/high |
| C | ... | ... | low/med/high |
Choice: [option name] — [single sentence reason]
Risks:
- [risk]
- [risk]
Next: [immediate first action]
Rules
- Table rows: 2–5 options. If more, group similar ones.
- Pro/Con: one phrase each. Not full sentences.
- Choice: lead with option name. One sentence reason. No hedging.
- Risks: 2–4 real blockers. Not generic "might take longer."
- Next: one concrete action, not a plan.
- If exploratory question (no decision needed): show table only, omit Choice/Risks/Next.
Example
Decision: session storage strategy for auth
| Option | Pro | Con | Complexity |
|---|---|---|---|
| JWT | stateless, no DB reads | can't revoke, large cookie | low |
| Redis | revocable, small cookie | infra dependency | medium |
| DB session | simple, no new infra | DB read every request | low |
Choice: Redis — revocability is required (security team req), team already operates Redis for cache
Risks:
- Redis downtime = full auth outage (add fallback or circuit breaker)
- Session data size can grow if not careful — set explicit TTLs
Next: Add ioredis to package.json, write src/lib/session.ts
One-shot. Does not persist.
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.
- 9d ago First seen · 54 lines · 40 tokens per session scan A 2a1083a8cc04
pith-arch is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 437 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 2026-08-30.
Other skills, from other repositories
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.