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 DefaultPerson/agent-setup --skill repo-contextgit clone --depth 1 https://github.com/DefaultPerson/agent-setupWrote 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/defaultperson/agent-setup/repo-context)<a href="https://agentmods.dev/skills/defaultperson/agent-setup/repo-context"><img src="https://agentmods.dev/badge/skills/defaultperson/agent-setup/repo-context/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/defaultperson/agent-setup/repo-context"><img src="https://agentmods.dev/badge/skills/defaultperson/agent-setup/repo-context.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 | $0.00023 | $0.00674 |
| Opus 5 | $0.00012 | $0.00337 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
repo-context 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo context
The snapshot below was collected before this prompt reached you. Treat it as ground truth and do not re-run these commands.
Snapshot
Root: !git rev-parse --show-toplevel 2>&1 | head -1
Git status:
git status -sb 2>&1 | head -15
Tracked files (total, then per top-level directory):
git ls-files 2>/dev/null | wc -l
git ls-files 2>/dev/null | awk -F/ 'NF>1{print $1}' | sort | uniq -c | sort -rn | head -25
File list (first 150):
git ls-files 2>/dev/null | head -150
Stack markers present:
ls -1d package.json pyproject.toml go.mod Cargo.toml requirements.txt uv.lock pnpm-lock.yaml Dockerfile docker-compose.yml compose.yaml Makefile .github/workflows 2>/dev/null || true
README (first 80 lines):
head -80 README.md 2>/dev/null || echo "(no README.md)"
AGENTS.md (first 60 lines):
head -60 AGENTS.md 2>/dev/null || echo "(no AGENTS.md)"
Recent activity:
git log --oneline -15 2>&1 | head -15
git diff --stat HEAD~5..HEAD 2>/dev/null | tail -15
Task
- Use the snapshot for structure, stack and recent activity. CLAUDE.md is already loaded — don't re-read it.
- Read at most 5 key files: entry points, core models/schemas, main config. Pick them from the file list; skip lockfiles, generated and vendored code.
- If the snapshot shows this is not a git repository, fall back to a top-level
lsand the README. - Output the summary below — bullets, no walls of text.
Output
## Project Context
### Overview
- **Purpose**: {what this project does}
- **Tech Stack**: {languages, frameworks, key deps}
### Architecture
- **Structure**: {key directories, patterns}
- **Entry Points**: {main files}
- **Config**: {build tools, CI/CD, infra}
### Current State
- **Branch**: {current branch}
- **Recent Work**: {last 5 commits, one line each}
- **Active Areas**: {most changed files/dirs}
### Key Files
- {path} — {purpose}
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.
- yesterday First seen · 84 lines · 23 tokens per session scan A bbb9177e8b2f
repo-context is a skill published in the GitHub repository DefaultPerson/agent-setup (11 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 674 once invoked, about $0.0001 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 2026-09-11.
Other skills, from other repositories
chronos
Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle…
decision-ledger
Maintain an append-only decision ledger (DECISIONS.md). Use when the user confirms a decision, reverses or changes a past decision, asks what was decided and why, or at session start to load standing decisions.
pin
Turn a correction or working preference the user just expressed into a permanent ballast rule. Use when the user corrects your behavior, says "don't do X" / "always do Y" / "I told you before", or asks you to remember how they want things done.
knowledge-base
Keep verified findings in memory/knowledge/ so the same research is never done twice. Use before researching any topic, when a finding passes the verify gate, or when about to answer from something learned in an earlier session.
catchup
Restore context after /clear by summarizing recent work and project state.
recall
Sweep everything the project already holds before answering — at the first message of a session, and again whenever the subject shifts to something the current thread was not about. Use before replying, not only before researching.