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/azrtydxb/procoder/indexgit clone --depth 1 https://github.com/azrtydxb/procoderWhat 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 | $0.00024 | $0.00657 |
| Opus 5 | $0.00012 | $0.00329 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
index 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 yesterday.
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
The user invoked /procoder:index with arguments: $ARGUMENTS
The command below is the procoder binary on PATH.
The index is your fast map of the codebase — reach for it before grepping:
procoder index build— build both tiers (universal-ctags broad, SCIP precise where the language has an indexer). Run this first, and rerun when stats says the index is stale.procoder index find <symbol>— where a symbol is defined (file:line, kind, signature).procoder index search <text>— fuzzy symbol search when you don't know the exact name.procoder index refs <symbol>— every reference; the output says whether it answered precise (SCIP) or textual (git grep).procoder index impls <symbol>— what implements an interface or its methods (precise tier only; it says so when that tier is absent).procoder index outline <file>— a file's symbols in order; read this before reading the whole file.procoder index impact— which symbols the working-tree change defines and which files reference them; verify those files before calling the work finished.procoder index callers <symbol>— who calls it and what it calls (precise tier).procoder index unused— dead-code candidates: defined, never referenced; exported API is marked, you judge it.procoder index entrypoints— main functions and the exported surface, the security starting set.procoder index graph— the full caller→callee edge list as JSON, for tools that walk reachability.procoder index stats— what's indexed and how fresh.procoder index rename <symbol> <newname> [--at path:line]— the cross-file rename as a reviewable unified diff (Go, computed by gopls; other languages get the reference worksheet instead). Nothing is written: review the diff, apply it yourself, then verify withindex refs <newname>andlint --typeswhere it applies.
If a command answers "no index" or names missing tools, run
procoder init and then procoder index build. Staleness notes in
the output are real — refresh before trusting line numbers.
The index is the fast, repo-wide map; a live language server is the
microscope. When a refs answer is textual or same-named symbols
collapse together, prefer your host's native LSP tool (goToDefinition,
findReferences) if one is configured — then come back to the index for
repo-wide sweeps, impls, callers, unused, and impact.
With arguments, run the matching subcommand directly and act on its output.
Without arguments, run stats and report the index's state.
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.
- yesterday First seen · 54 lines · 24 tokens per session scan A 7c8876684572
index is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 657 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
setup
Initialize a new project with SDLC-compliant structure. Creates required files, configures build system, sets up CI/CD, and establishes quality tooling.
validate
Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.
run-tests
Run automated functional tests using the hook-driven test framework. Execute the test suite to validate all project functionality.
test-report
Generate test execution report in markdown format.
add-test
Interactively add a new test definition to the test suite.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.