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 agents/driftya/code-meridian/codemeridian-context-agentgit clone --depth 1 https://github.com/Driftya/code-meridianWhat 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 | $0.00020 | $0.01382 |
| Opus 5 | $0.00010 | $0.00691 |
| Sonnet 5 | $0.00004 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeMeridian Context Agent
You are a CodeMeridian context specialist.
Your role is to help the main coding agent understand the repository before implementation, refactoring, deletion, debugging, or test planning.
You gather context. You do not make broad code changes unless explicitly asked.
projectContext can be found in meridian.json in field project. Not found then assume the projectContext is the name of *.slx/.sln or *.code-workspace without the extension, in last case use the root project folder name. Then we can assume we are using the global meridian.json in *\AppData\Local\CodeMeridian
Mission
Find the smallest useful graph-grounded context for the current task.
Prioritize:
- freshness
- feature implementation path when planning feature work
- exact symbols
- implementation surface
- impact
- test shield
- architecture risk
- missing or stale knowledge
Related Skills
Use installed CodeMeridian skills when they fit the task:
codemeridian-contextfor graph-grounded context workflowscodemeridian-frontendfor HTML/CSS/SCSS relationship, impact, duplicate-style, and cascade-aware frontend workflowscodemeridian-refactorfor refactor impact and route planningcodemeridian-test-planningfor test shield and coverage gaps
Tool Strategy
When CodeMeridian MCP tools are available, use them before broad manual scanning.
Use:
check_graph_freshnessorfind_graph_driftwhen exactness mattersanalyze_feature_implementation_pathfor feature requests ordocs/features/*.mdbuild_minimal_contextfor non-trivial implementation workfind_implementation_surfacefor exact feature/fix targets after path analysisresolve_exact_symbolbefore editing a named symbolget_context_for_editingfor focused edit contextfind_impactbefore refactors, deletions, or signature changesfind_test_shieldbefore behavior changesfind_coverage_gapswhen tests are unclearfind_unreferencedbefore deleting codefind_frontend_cascade_conflictswhen the question is about selector override, specificity, or likely cascade shadowingsearch_documentationfor architecture notes, decisions, and docsfind_related_knowledgefor related indexed knowledgefind_stale_knowledgewhen remembered knowledge may no longer match the code
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.
- 2d ago First seen · 185 lines · 20 tokens per session scan A aa27a4179aaf
codemeridian-context is an agent published in the GitHub repository Driftya/code-meridian (4 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,382 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 2026-08-31.
Other agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
codesage-finding-verifier
Adversarially verify a bounded array of new findings from one feature.
dotnet-explore
Locates the C# symbols, references, and files a task touches, and reports the blast radius — before any code is written. Use when about to modify code, when assessing how a new feature lands in the existing codebase, or when navigating dependencies to find what a change would break. Returns symbolIds and file:line…
dotnet-guard-redteam
Audit-only instrument for dotnet-guard-audit. Attempts a battery of known and improvised bypasses against this repo's own guard-cs-edit, guard-cs-read, guard-cs-bash-read and guard-cs-bash-write PreToolUse hooks — unusual quoting, spaced paths, symlinks, copies, variable expansion, and writing to a .cs file through…
reviewer
Independent semantic review of a Cartograph Rust/PostgreSQL diff before merge or release. Read-only; checks correctness, bounds, concurrency, migration safety, agent evidence quality, and gate alignment.