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 ProsusAI/prism --skill publish-skillsgit clone --depth 1 https://github.com/ProsusAI/prismWrote 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/prosusai/prism/publish-skills)<a href="https://agentmods.dev/skills/prosusai/prism/publish-skills"><img src="https://agentmods.dev/badge/skills/prosusai/prism/publish-skills/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/prosusai/prism/publish-skills"><img src="https://agentmods.dev/badge/skills/prosusai/prism/publish-skills.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 | $0.03629 |
| Opus 5 | $0.00027 | $0.01814 |
| Sonnet 5 | $0.00011 | $0.00726 |
| Haiku 4.5 | $0.00005 | $0.00363 |
Grade A, and why
publish-skills scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Build the request payload and POST to the registry Worker API. Use Python for the HTTP call (not curl/jq) to handle JSON encoding of SKILL.md content with special characters correctly. How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Use when the user wants to publish extracted or promoted skills to a Prism skill registry. Invoked as /publish-skills (Claude Code) or @publish-skills (Cursor), optionally with flags: --all (publish everything regardless of delta state) or --registry NAME (target a named registry).
Prerequisites
- Skills must exist in
_analysis/extracted_skills_codebase/(created by/extract-skills(Claude Code) or@extract-skills(Cursor), orprism promote) and/or_analysis/extracted_skills_history/(created by/run-history-pipeline(Claude Code) or@run-history-pipeline(Cursor)) - Each skill directory must contain both
plugin.jsonandSKILL.md - A registry must be configured in
~/.prism/registries.json(or legacy~/.prism/config.json) - The
REGISTRY_TOKENenvironment variable or per-registry token inregistries.jsonmust be available
Flags
| Flag | Effect |
|---|---|
--all |
Publish all valid skills, ignoring delta state (force republish) |
--registry NAME |
Target a specific named registry from registries.json. If omitted, uses the default registry. The target must have writable: true. |
Instructions
Step 1 -- Resolve target registry
Resolve the target registry from ~/.prism/registries.json (with fallback to legacy ~/.prism/config.json). If --registry NAME was specified, use that name; otherwise use the default registry.
python3 -c "
import json, os, sys
reg_path = os.path.expanduser('~/.prism/registries.json')
try:
with open(reg_path) as f:
data = json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
data = {'registries': [], 'default': None}
# Fall back to config.json migration
if not data.get('registries'):
cfg_path = os.path.expanduser('~/.prism/config.json')
try:
with open(cfg_path) as f:
cfg = json.load(f)
url = cfg.get('registry_url', '')
if url:
print(json.dumps({'name': 'default', 'url': url, 'token': '', 'writable': True}))
sys.exit(0)
except: pass
print('NOT_CONFIGURED')
sys.exit(0)
# Resolve target: --registry NAME or default
target_name = None # <-- set to registry name if --registry flag was provided
if target_name is None:
target_name = data.get('default')
if not target_name:
print('NO_DEFAULT')
sys.exit(0)
for reg in data['registries']:
if reg['name'] == target_name:
if not reg.get('writable', True):
print('READ_ONLY:' + target_name)
sys.exit(0)
print(json.dumps(reg))
sys.exit(0)
print('NOT_FOUND:' + str(target_name))
"
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.
- 11d ago First seen · 382 lines · 54 tokens per session scan A b8889ce49dbd
publish-skills is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 3,629 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…