A local system for collecting verified evidence from a developer’s GitHub repositories, pull requests, and commits, then turning it into possible resume material. It keeps an experience index that can be used when matching a resume to a job description.

Use it to add a GitHub URL, gather the relevant author’s work, build a tagged experience index, and identify skills or evidence for truthful resume bullets. The collected files stay under the local CoForce experience directory.

It reduces the work of finding relevant past projects and writing resume bullets from memory. It limits GitHub scans to setup or an explicit refresh, so routine resume campaigns can use the saved local evidence.

experience — Skill for Claude Code and Codex by Sma1lboy: A local system for collecting verified evidence from a…

Install

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.

agentmods

npx agentmods add skills/sma1lboy/coforce-apply/experience

Any agent

npx skills add Sma1lboy/coforce-apply --skill experience

Clone the repo

git clone --depth 1 https://github.com/Sma1lboy/coforce-apply

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/experience.svg)](https://agentmods.dev/skills/sma1lboy/coforce-apply/experience)

Your own site

<a href="https://agentmods.dev/skills/sma1lboy/coforce-apply/experience"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/experience.svg" alt="Measured on agentmods" height="20"></a>

Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,423 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00150	$0.03423
Opus 5	$0.00075	$0.01711
Sonnet 5	$0.00030	$0.00685
Haiku 4.5	$0.00015	$0.00342

Measured 5d ago against content hash 44051604e897, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

experience 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 5d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/evidence/__init__.py, scripts/evidence/common.py, scripts/evidence/github_evidence.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/experience/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experience — Tier 0 source of truth

Tier 0 is the only CoForce layer allowed to scan GitHub. It runs once during setup and again only when the user explicitly asks to refresh. /start, /campaign, and per-JD matching must never call GitHub or refresh this index.

Position in the two-module design: the evidence this skill collects is Module-1 raw material — context for generating truthful bullets (see "Repo → STAR bullets" below) plus experience-derived skill candidates. Bullets still require user review into profile.json. Module 2 selects those reviewed bullets directly (campaign.mjs pool) and merges the local experience-index.json.skills[] with the user's resume/coursework skills and optional profile evidence enrichments. This is a local data read only; campaigns never refresh or call GitHub.

All output stays under ~/.coforce/experience/:

experience/
├── sources.json
├── github-evidence/
│   ├── raw/
│   └── library/
├── experience-index.json
└── manifest.json

Commands

The CLI lives at scripts/experience.mjs relative to this skill.

Add a source from a URL — normal user flow

When the user sends a GitHub repository, PR, or commit URL, process it directly. Do not ask the user to fill in repo, author, or edit sources.json.

node "<experience-skill>/scripts/experience.mjs" source add "https://github.com/owner/repository"
node "<experience-skill>/scripts/experience.mjs" source add "https://github.com/owner/repository/pull/42"
node "<experience-skill>/scripts/experience.mjs" source add "https://github.com/owner/repository/commit/abc123"

Author inference is intentionally small and predictable:

repository URL → the currently authenticated gh user;
pull-request URL → that PR's author;
commit URL → the linked GitHub commit author, falling back to the authenticated gh user when GitHub has no linked account.

After adding, tell the user the inferred owner/repo ← author mapping. Ask for a correction only if that inference is wrong. An explicit override is available for the agent or advanced use, and does not call GitHub:

Read the full file on GitHub · 295 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

5d ago First seen · 295 lines · 150 tokens per session scan A 44051604e897

Subscribe to this mod's changes

experience is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 6d ago), licensed MIT. It adds 150 tokens to every session and 3,423 once invoked, about $0.0007 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens