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 getpapi/papi --skill papi-ideagit clone --depth 1 https://github.com/getpapi/papiWrote 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/getpapi/papi/papi-idea)<a href="https://agentmods.dev/skills/getpapi/papi/papi-idea"><img src="https://agentmods.dev/badge/skills/getpapi/papi/papi-idea/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/getpapi/papi/papi-idea"><img src="https://agentmods.dev/badge/skills/getpapi/papi/papi-idea.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 | $0.00026 | $0.01009 |
| Opus 5.5 | $0.00010 | $0.00404 |
| Sonnet 5.5 | $0.00005 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
papi-idea 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 today.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
papi-idea
Reusable skill or method drafts
When the user asks to make, create, write, or draft a reusable skill or method, produce a reviewable SKILL.md through the caller's native file/skill mechanism. An ambiguous artifact request should not become a generic idea or note. The idea tool recognizes this intent in unstructured text and returns bounded drafting guidance without writing a backlog task or document. It does not generate the artifact through a server-side model.
Read the target project's own canon and tailor the draft to the actual request. Include frontmatter name and description with an invocation trigger, purpose, required inputs, ordered steps, expected result, scope boundaries, and concrete verification. Keep reusable methods project-agnostic; resolve project-specific paths and policies when invoked. Show the finished draft for review. Do not install, execute, or publish it implicitly.
When the user requests saving in PAPI, register the finalized complete body with existing doc_register as framework or guide, private by default, and verify exact project-scoped body read-back. Use the existing docs index convention for a saved workspace document. No separate skill entity is needed.
Explicit requests to file a task or bug remain FILE-ONLY, including “file a task to fix skill installation.” Structured type, discovery, or scope_class=task also retains its existing intake route. Draft creation and backlog filing are distinct caller intents.
Idea Pipeline (unlocked at cycle 21)
The idea tool is your backlog intake — not just for features, but bugs, research, and big ideas.
FILE-ONLY mode for filing requests
When the user explicitly asks to file, submit, capture, or add an idea, bug, research item, or document to the backlog, enter FILE-ONLY mode for that request:
- Gather only the minimum intake information and perform the required project-scoped PAPI operation, including the receipt, duplicate check,
Reference:line, and any required documentation-index maintenance. - Do not read source files or inspect the implementation. Do not edit source or configuration files, create a branch or commit, run tests or builds, or begin implementing the filed item.
- After the filing operation is recorded, stop and report the durable result. Do not continue into implementation unless the user explicitly asks to build or fix it.
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.
- today First seen · 70 lines · 26 tokens per session scan A 2bd5ccb3e40a
papi-idea is a skill published in the GitHub repository getpapi/papi (11 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,009 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
trace
Resolve a stack trace or error message to the code responsible, using Synapse's code graph. Use when the user pastes a stack trace or asks where an error comes from. Needs Synapse Pro.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.