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 commands/postrv/narsil-mcp/analyze-functiongit clone --depth 1 https://github.com/postrv/narsil-mcpWhat 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 | $0.00018 | $0.00394 |
| Opus 5 | $0.00009 | $0.00197 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
analyze-function 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 3d 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.
What it actually says
Analyze Function
Perform a deep analysis of a specific function to understand its role, complexity, and impact.
Prerequisites
This command requires the --call-graph flag to be enabled when starting narsil-mcp. Check get_index_status to verify.
Workflow
The user should provide a function name. Parse $ARGUMENTS to extract:
- Repository name (if provided)
- Function name (required)
-
Find the function: Use
workspace_symbol_searchto locate the function if the exact location is unknown -
Get the source: Use
get_symbol_definitionto read the function code -
Analyze callers: Use
get_callerswithtransitive=trueandmax_depth=3to see what calls this function -
Analyze callees: Use
get_calleeswithtransitive=trueto see what this function calls -
Check complexity: Use
get_complexityto get cyclomatic and cognitive complexity metrics -
Data flow (if path is known): Use
get_data_flowto understand variable definitions and uses -
Control flow (if path is known): Use
get_control_flowto see branches and loops -
Summarize:
- Function purpose (based on code and naming)
- Complexity assessment (simple/moderate/complex)
- Dependency analysis (what it depends on, what depends on it)
- Risk assessment for modifications
- Suggestions for refactoring if complexity is high
Arguments
Function to analyze: $ARGUMENTS
Example usage:
/narsil:analyze-function handle_request/narsil:analyze-function myrepo process_payment
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.
- 3d ago First seen · 47 lines · 18 tokens per session scan A fbfed3a7a295
analyze-function is a command published in the GitHub repository postrv/narsil-mcp (181 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 394 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 2026-08-30.
Other commands, from other repositories
localnest:recall
Recall relevant memories for the current task or query.
localnest:remember
Save a decision, fact, or learning to LocalNest memory.
localnest:prime
Get full task context — memories, entities, files, changes, and actions in one call.
localnest:fact
Add a structured fact to the knowledge graph.
localnest:ingest
Ingest a conversation file into memory and knowledge graph.
localnest:onboard
Run the guided first-run setup wizard that configures everything automatically.