Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgenpx agentmods add skills/firstp1ck/pi-coding-agent-forge/learningsWrote 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/firstp1ck/pi-coding-agent-forge/learnings)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/learnings"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/learnings/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/firstp1ck/pi-coding-agent-forge/learnings"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/learnings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 70 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.01054 |
| Opus 5.5 | $0.00022 | $0.00422 |
| Sonnet 5.5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
learnings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LEARNINGS
This skill manages and uses Firstpick's durable troubleshooting LEARNINGS archive.
The archive is not chat memory. It is a local, file-based knowledge base of short solved-issue notes plus generated indexes and summaries.
When to use
Use this skill when:
- a troubleshooting issue looks similar to something solved before
- the user asks about LEARNINGS,
/ret-LEARNINGS, or/sum-LEARNINGS - a troubleshooting session ended with a real solution and should be recorded
- the LEARNINGS symlink/env/timer/scripts need inspection or repair
Do not blindly apply a past solution. Always verify against current files, commands, logs, and system state.
Path resolution
Resolve the archive root in this order:
- Source
~/.pi/agent/learnings.envif present and use$LEARNINGS_DIR. - Otherwise use the stable symlink
~/.pi/agent/LEARNINGS. - Otherwise ask before creating a new archive.
Expected current value on Firstpick's system:
/mnt/SSD_NVME/LEARNINGS
Portable shell snippet:
source "$HOME/.pi/agent/learnings.env" 2>/dev/null || true
LEARNINGS_DIR="${LEARNINGS_DIR:-$HOME/.pi/agent/LEARNINGS}"
Retrieval workflow
- Resolve
LEARNINGS_DIR. - Read
$LEARNINGS_DIR/LEARNINGS-SUMMARY.md. - Identify relevant entries.
- Read the referenced
sourceorarchivefile for each relevant entry. - Apply the lesson only after verifying the current system/repo state.
- In the final answer, briefly cite which LEARNINGS files influenced the solution.
If LEARNINGS-SUMMARY.md is missing or stale, run:
~/.pi/agent/bin/learnings-summary
or, from this skill directory, using paths relative to the skill root:
../../scripts/sync-learnings.py
../../scripts/summarize-learnings.py
Adding a learning
This is an implicit completion requirement, not an optional reminder.
At the end of every troubleshooting/configuration/repair task where a real solution was found, automatically create or update one concise LEARNINGS .md note before the final answer. Do not wait for the user to ask. This applies especially when this skill was used for inspection, repair, cleanup, setup, repeated-issue retrieval, or LEARNINGS maintenance.
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.
- 1mo ago First seen · 135 lines · 54 tokens per session scan A 495e6d532a03
learnings is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,054 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
clawmem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring, and memory lifecycle (pin/snooze/forget). Use when tuning retrieval, troubleshooting recall quality, or any ClawMem…
gelatiere
Use this when you receive a [Sprinkle Event: gelatiere] lick with action: 'gelatiere-suggestions' — the gelatiere (SLICC's resident advisor) delivered suggestions: skills to install, use cases to try, habits to change, skills worth writing, bugs worth filing against SLICC — or an inline dip lick with action…
memory
Use this when the user asks what SLICC remembers, why a remembered fact is missing or stale, whether memory curation ran, to re-run curation for an archived session, or to consolidate a bloated memory file. Covers the memory shell command (show, status, log, curate, dream), the per-cone memory files, and the curation…