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 agentmods add skills/markoblogo/abvx-agent-skills/git-native-context-contractnpx skills add markoblogo/abvx-agent-skills --skill git-native-context-contractgit 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/git-native-context-contract)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/git-native-context-contract"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/git-native-context-contract.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.01527 |
| Opus 5 | $0.00046 | $0.00763 |
| Sonnet 5 | $0.00018 | $0.00305 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
git-native-context-contract 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.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git-Native Context Contract
Use this skill to retain a small amount of durable project truth in reviewable Markdown. It is opt-in and provider-neutral. It does not install Archcore, configure MCP, add hooks, inject session context, or create a competing memory runtime.
Authority and storage
Prefer the repository's existing documentation layout: docs/, docs/ai/, docs/adr/, architecture records, or another documented project-owned path. Create a new context directory only when the user explicitly requests one or no suitable durable location exists.
Project truth already encoded in code, tests, signed agreements, product contracts, protected evidence stores, runtime ledgers, or approved docs remains authoritative. Never copy secrets, private customer data, protected evidence, transcripts, or hidden reasoning into these documents.
All writes are proposal-first:
proposal -> inspect -> apply
Minimal types
Use only:
adr: a finalized architecture or technical decision, alternatives, and consequences.rfc: a significant proposed change still open for review.rule: an imperative engineering or operating standard with enforcement guidance.spec: a normative behavior contract for a component, interface, schema, protocol, or subsystem.plan: bounded implementation work with dependencies, acceptance criteria, and verification.rnd: a time-boxed investigation ending in a recommendation and next action.cpat: a durable code-change or incident pattern.
Do not invent another type because the topic feels different. Additional types require an explicit project-level contract change.
Type selection
- Decision already made:
adr; still proposed:rfc. - Required human/team practice:
rule; required system behavior:spec. - Open question:
rnd; committed execution sequence:plan. - Reusable lesson from a defect, incident, CI failure, or production/runtime repair:
cpat.
If none fits, do not create a document.
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.
- 5d ago First seen · 179 lines · 91 tokens per session scan A 448be1ad266a
git-native-context-contract is a skill published in the GitHub repository markoblogo/abvx-agent-skills (15 stars, last pushed 11d ago), licensed MIT. It adds 91 tokens to every session and 1,527 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
weave
Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
customer-deck-builder
Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.
premortem
First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.
bcc-plan-spar
BCC align+lock+review PLAN.md for one slice (no product code). Slash: /bcc-plan-spar · chat: bcc:plan-spar · "lock PLAN" · spar the plan. Args: rounds=N (auto-review cap), review=self|subagent|cli|auto|off. Grill until clear enough (no default Q&A quota). Hand off to bcc-clean-cut after human APPROVE.