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 lossless-group/lossless-agent-skills --skill context-vigilancegit clone --depth 1 https://github.com/lossless-group/lossless-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/lossless-group/lossless-agent-skills/context-vigilance)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/context-vigilance"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/context-vigilance/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/lossless-group/lossless-agent-skills/context-vigilance"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/context-vigilance.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 | $0.00142 | $0.07399 |
| Opus 5 | $0.00071 | $0.03700 |
| Sonnet 5 | $0.00028 | $0.01480 |
| Haiku 4.5 | $0.00014 | $0.00740 |
Grade A, and why
context-vigilance 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 12d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Vigilance
A framework for Human + AI collaboration: manage the context available to AI and collaborators with the same rigor you manage code. Every Lossless project has a context-v/ directory with (commonly) eight subdirectories, organized into three cognitive modes: Prep, Reflective, and Journey — plus two universal utility folders and a small experimental tier still finding its shape.
Norms, not rules. Patterns here are loosely enforced. The team is generative-first; consistency emerges when attention focuses on a project, file, or pattern. Be generous reading existing files (they may pre-date current norms or be experiments) and careful writing new ones. See references/philosophy.md for the deeper rationale.
Drift policy: When you encounter inconsistencies (mismatched frontmatter, deviating filenames, partial-convention adoption), observe, note, surface, but do not auto-fix as a side effect of unrelated work. Cleanup happens only with explicit user permission. The user runs parallel agent sessions; silent normalization creates conflicts. (This rule lives globally in ~/.pi/agent/AGENTS.md; restated here for redundancy.)
Reference: https://www.lossless.group/projects/gallery/context-vigilance
When to use this skill
- The user asks you to create or edit any file under a
context-v/directory - The user mentions specs, prompts, blueprints, reminders, explorations, or issues in the Lossless sense
- Starting a new project and setting up
context-v/ - The user asks about context engineering, AI co-development, or "the context-v thing"
The Eight Directories
Prep Mode (spec → plan → prompt)
The work of deciding what to build is the work — "prep" here is not "minor pre-work", it's the deliberate forward construction phase. Specs, plans, and prompts are the artifacts, in descending altitude.
context-v/specs/— Living specifications. What you're building and why. Constantly updated. Single source of truth. Every prompt references a spec.context-v/plans/— Actionable work plans: sequenced, scoped, closer to execution than a spec but not yet the step-by-step of a prompt. The natural home for agent-produced plans (plan-mode output, migration sequences, refactor roadmaps). Promoted to canon 2026-07-21 after appearing organically in 14 repos — the most-adopted folder the original six didn't name.context-v/prompts/— Step-by-step, prompt-by-prompt implementation documents (NOT single chat messages). Each prompt references specs/plans/blueprints/reminders. Success at each step is verifiable before moving on.
What ships with it
12 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.
- references/developing-a-spec.md 10.0 KB
- references/doc-type-guide.md 4.5 KB
- references/frontmatter-spec.md 40 KB
- references/philosophy.md 7.0 KB
- references/status-discipline.md 7.5 KB
- references/versioning.md 3.5 KB
- templates/blueprint.md 1.3 KB
- templates/exploration.md 1.4 KB
- templates/issue.md 1.5 KB
- templates/prompt.md 1.4 KB
- templates/reminder.md 1.1 KB
- templates/spec.md 1.8 KB
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.
- 12d ago First seen · 326 lines · 142 tokens per session scan A ded05d6d6edc
context-vigilance is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 142 tokens to every session and 7,399 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.
Other skills, from other repositories
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
close-session
An end-of-session workflow that reviews new lessons, asks before promoting repeated patterns, refreshes memory files, and writes a handoff.
aictx
Use this skill when working in a repository that uses AICTX for repo-local operational continuity. Prefer AICTX MCP tools when available, fall back to CLI commands, resume before substantial work, and finalize factual continuity after work.
tour
An interactive walkthrough of the Memory Kit system using the files in the current project. It explains how session handoffs, task backlogs, and stored project memory fit together.
journal-optimizer
Guided database pruning and optimization workflows for memory-journal-mcp. Uses importance scores, relationship density, and entry metadata to identify low-value entries for safe soft-deletion. Includes dry-run previews, backup gates, and revert guidance. Use when the user says "clean up the database", "optimize…
init
Initialize structured context for this project. Scaffolds .scs/ with all 11 concern bundles, scans the project, and recommends where to start.