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 postrv/narsil-mcp --skill narsilgit clone --depth 1 https://github.com/postrv/narsil-mcpWrote 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/postrv/narsil-mcp/narsil)<a href="https://agentmods.dev/skills/postrv/narsil-mcp/narsil"><img src="https://agentmods.dev/badge/skills/postrv/narsil-mcp/narsil/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/postrv/narsil-mcp/narsil"><img src="https://agentmods.dev/badge/skills/postrv/narsil-mcp/narsil.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 | $0.00042 | $0.02556 |
| Opus 5 | $0.00021 | $0.01278 |
| Sonnet 5 | $0.00008 | $0.00511 |
| Haiku 4.5 | $0.00004 | $0.00256 |
Grade A, and why
narsil 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 10d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narsil Code Intelligence
Narsil is an MCP server providing 90 code intelligence tools (plus 2 prompts: explain_codebase, find_implementation). This skill helps you use them effectively.
Critical: Parameter Naming
Use short parameter names. These are the most common mistakes:
| Wrong | Correct |
|---|---|
repo_path |
repo |
symbol_name |
symbol |
file_path |
path |
function_name |
function |
The repo parameter expects the repository name from list_repos, not the full filesystem path.
Getting Started
Always start with:
list_repos → See indexed repositories
get_index_status → See which features are enabled
Feature Requirements
Some tools require specific CLI flags when starting narsil-mcp:
| Feature | Required Flag | Tools |
|---|---|---|
| Git integration | --git |
get_blame, get_file_history, get_recent_changes, get_hotspots, get_contributors, get_commit_diff, get_symbol_history, get_branch_info, get_modified_files |
| Call graph | --call-graph |
get_call_graph, get_callers, get_callees, find_call_path, get_complexity, get_function_hotspots |
| LSP | --lsp |
Enhanced: get_hover_info, get_type_info, go_to_definition |
| Neural search | --neural |
neural_search, get_neural_stats |
| Remote repos | --remote (+ GITHUB_TOKEN) |
add_remote_repo, list_remote_files, get_remote_file |
| Knowledge graph | --graph |
sparql_query, list_sparql_templates, run_sparql_template, get_ccg_manifest, export_ccg_*, query_ccg, import_ccg, import_ccg_from_registry, get_ccg_acl, get_ccg_access_info |
If a tool returns empty results or errors, check get_index_status to verify the feature is enabled.
Relevant environment variables
| Var | Purpose |
|---|---|
GITHUB_TOKEN |
Auth for --remote GitHub API calls |
EMBEDDING_API_KEY / VOYAGE_API_KEY / OPENAI_API_KEY |
Neural embedding provider key |
EMBEDDING_SERVER_ENDPOINT |
Custom/self-hosted embeddings endpoint |
RUST_LOG |
Logging level (debug, info, warn, error) |
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.
- 10d ago First seen · 249 lines · 42 tokens per session scan A 163b347acb46
narsil is a skill published in the GitHub repository postrv/narsil-mcp (182 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,556 once invoked, about $0.0002 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
trace-mcp
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
cel-debugging
Diagnosing and resolving Common Expression Language (CEL) compilation and evaluation errors.
claude
Skill "claude" from paladini/locus-mcp, covering claude code skill (stub), when to use locus, when to use grep, mcp registration and status.
qartez
Semantic code intelligence skill for qartez MCP. Use qartez tools for code exploration, impact analysis, and guarded refactors; treat built-in code-tool denials as routing signals and recover via qartez replacements.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.