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 markoblogo/abvx-agent-skills --skill project-context-bootstrapgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/project-context-bootstrap)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/project-context-bootstrap"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/project-context-bootstrap/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/markoblogo/abvx-agent-skills/project-context-bootstrap"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/project-context-bootstrap.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 | $0.00072 | $0.00595 |
| Opus 5 | $0.00036 | $0.00298 |
| Sonnet 5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
project-context-bootstrap 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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context Bootstrap
Create a compact, durable working model of a repo before the agent starts inventing one from guesswork.
Goal
Turn a repo with weak or missing agent-facing context into a repo with:
- a clear stack and structure summary;
- known commands and verification paths;
- durable context files or notes with real content;
- explicit approval before reorganizing existing docs.
Workflow
- Detect
- inspect project manifests, lockfiles, workspace layout, test commands, and major directories;
- detect whether context already exists:
AGENTS.md,docs/ai/, runbooks, plans, or other agent-facing docs.
- Study existing context first
- if the repo already has useful docs, read them before proposing replacements;
- separate what looks good, stale, missing, or conflicting.
- Ask
- have a real project-discovery conversation with the user;
- cover what the product is, who uses it, main features, risky areas, workflow conventions, and external dependencies;
- follow up until the project is actually understandable.
- Summarize
- restate your understanding in concise project language;
- confirm accuracy before writing or reorganizing context.
- Propose
- suggest the smallest useful context structure:
- top-level
AGENTS.mdor compact startup doc; docs/ai/architecture.md;docs/ai/how-to-test.md;- task-specific notes only if needed;
- top-level
- ask before reorganizing or overwriting anything durable.
- suggest the smallest useful context structure:
- Populate
- write real content from code and user input, not placeholders;
- include concrete commands, file paths, key modules, and current conventions.
- Validate
- verify the new context is small, accurate, and actually useful for the next session.
Existing Repo Rules
- Preserve good context; do not replace it with generic scans.
- Show what you want to keep, improve, and add before changing layout.
- Never silently move or delete user-written docs.
Compression Rules
What ships with it
2 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.
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.
- 9d ago First seen · 66 lines · 72 tokens per session scan A abf148a9f170
project-context-bootstrap is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 595 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.