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 Driftya/code-meridian --skill codemeridian-contextgit clone --depth 1 https://github.com/Driftya/code-meridianWrote 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/driftya/code-meridian/codemeridian-context)<a href="https://agentmods.dev/skills/driftya/code-meridian/codemeridian-context"><img src="https://agentmods.dev/badge/skills/driftya/code-meridian/codemeridian-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/driftya/code-meridian/codemeridian-context"><img src="https://agentmods.dev/badge/skills/driftya/code-meridian/codemeridian-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 | $0.00036 | $0.02869 |
| Opus 5.5 | $0.00014 | $0.01148 |
| Sonnet 5.5 | $0.00007 | $0.00574 |
| Haiku 4.5 | $0.00004 | $0.00287 |
Grade A, and why
codemeridian-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 11d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeMeridian Context Skill
Use this skill when working in a repository indexed by CodeMeridian.
The goal is to gather the smallest useful context pack before reading many files or making code changes.
Resolve Project Context From The Target
Resolve scope before querying the graph. Start from each user-supplied file's parent or target directory, rather than assuming the current working directory owns every target.
- Resolve the absolute path and owning Git/worktree root (
git -C <directory> rev-parse --show-toplevelwhen available). A.gitfile also marks a worktree/submodule boundary. For a new path, start from its nearest existing parent. For a non-Git directory, use the enclosing configured project or solution/workspace root. - Inspect the nearest applicable
meridian.jsonon that ancestor chain, including the owning root, and read itsproject. Do not continue into an unrelated parent repository. A nested config may define a separately indexed subproject inside the same Git repository. - Honor a project context explicitly supplied for that target by the user or established by its actual index invocation. Global configuration, an inherited
CodeMeridian_Project, or the current repository's config is not evidence that an external target belongs to that context. If local identity is missing, solution (.sln/.slnx), workspace, package and root-folder names are candidates; confirm with a bounded graph lookup of a known file/symbol and its returnedprojectContext. State unresolved ambiguity instead of silently selecting a name. - Keep a scope map: target path, owning/index root, project context, identity evidence, and freshness. Convert file hints relative to that target's index root. A
.csproj/framework build scope is distinct from the repository's graph project context. Resolve each external target independently; a path outside the current checkout is useful context, not grounds for discarding it or automatically assigning a different project name. - Query the resolved context with
check_graph_freshness,resolve_exact_symboland the normal context tools. Use returned canonical node IDs; never fabricate IDs by prefixing the current project. If the target is unindexed, keep its source/config as explicitly unindexed evidence and continue useful scoped work.
What ships with it
1 file 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.
- 11d ago Changed · +40 lines · +7 tokens per session dc7c0919a4c5
- 23d ago Changed · +11 lines 11b788080161
- 1mo ago First seen · 163 lines · 29 tokens per session scan A daa5f1ad2d9d
codemeridian-context is a skill published in the GitHub repository Driftya/code-meridian (5 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 2,869 once invoked, about $0.0001 per session on Opus 5.5. 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
memtrace-decision-memory
Use Cortex decision memory through the normal Memtrace MCP tools. Trigger for free-text questions about what was decided, chosen, rejected, banned, or established as a convention; for why a symbol exists or which contracts constrain it; for whether a known decision held, drifted, or was violated; and for the…
memtrace-index
Index a source-code repo into the Memtrace knowledge graph and poll the job to completion. Use when the user asks to index, parse, ingest, reindex, watch, or prepare a source-code repo for Memtrace analysis, when code exploration needs an index, or when searches return 0/partial results for source paths under an…
memtrace-session-continuity
Catch up on everything that changed in an indexed source-code repo since the last session, using stored session anchors and Memtrace change memory. Use when the user asks to continue, catch up, resume, see what changed while away, recover prior context, or orient at session start without guessing timestamps. Do not…
memtrace-continuous-memory
Keep the Memtrace index fresh while editing by watching a repo for live, incremental re-indexing. Use when the user asks to keep Memtrace fresh while editing, watch a repo, enable live or incremental indexing, set up always-on memory (meaning Memtrace index watching, not generic agent memory), or make just-saved…
graph
Whole-codebase structural map of the codanna index as one self-contained HTML disc. Wedges per top-level module, concentric rings with hubs at the centre, hover or click a symbol to light its edge web, search, hide or highlight modules, brush a date range on the ribbon timeline (symbols dated by git blame), heatmap of…
x-ray
Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.