What is sigmap AGENTS.md?

Instructions for SigMap, a tool that creates searchable summaries of a codebase for coding agents.

Updating generated context, finding relevant files, checking configuration, and judging whether an agent's answer is grounded in the code.

They prevent generated summaries from overwriting human notes and require agents to use SigMap before searching files.

How manojmallick/sigmap configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to manojmallick/sigmap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/manojmallick/sigmap/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/manojmallick/sigmap

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/manojmallick/sigmap/agents-md/github.svg)](https://agentmods.dev/instructions/manojmallick/sigmap/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/manojmallick/sigmap/agents-md"><img src="https://agentmods.dev/badge/instructions/manojmallick/sigmap/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/manojmallick/sigmap/agents-md"><img src="https://agentmods.dev/badge/instructions/manojmallick/sigmap/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15,757 This file is loaded in full into every session.

When invoked 15,757 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.15757	$0.15757
Opus 5.5	$0.06303	$0.06303
Sonnet 5.5	$0.03151	$0.03151
Haiku 4.5	$0.01576	$0.01576

Measured 1mo ago against content hash 6219950bb005, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sigmap AGENTS.md 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 1mo 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.

AGENTS.md · 1,083 lines

How it starts

The opening of the file, as written. The whole thing — 1,083 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SigMap — AGENTS.md

Instructions for Codex-style agents working in this repository.

Append Strategy (Required)

When writing generated signature content, never overwrite human-written notes above the auto-generated marker. Everything above the marker (like these notes) is preserved verbatim; everything below it is regenerated by gen-context.js.

Each generated context file carries one canonical SigMap commands guidance block (emitted from formatOutput, identical across every context file). Signatures keep their full parameter lists and return types — the token budget drops whole low-priority files rather than collapsing signatures to bare line anchors.

Auto-generated signatures

Code signatures

SigMap commands

When	Command
Before answering a question about code	`sigmap ask "<your question>"`
To rank files by topic	`sigmap --query "<topic>"`
After changing config or source dirs	`sigmap validate`
To verify an AI answer is grounded	`sigmap judge --response <file>`

Always run sigmap ask (or sigmap --query) before searching for files relevant to a task.

todos

gen-context.js:27247  # TODO: s');

changes (last 5 commits — 8 minutes ago)

src/deps/inventory.js                         +readText  +readJson  +exists  +stripXmlComments
src/deps/sbom.js                              +isExactVersion  +normalizeVersion  +purlEncode  +purlFor
src/extractors/dispatch.js                    ~extractFile  ~langFor
src/extractors/pipeline.js                    +platformFor  +sniffPlatform  +stripInlineComment  +unquote
src/extractors/yaml.js                        ~extract
src/graph/builder.js                          ~extractFileDeps  ~build  ~_configuredSrcDirs  ~buildFromCwd
src/graph/impact.js                           ~isRouteFile  ~getImpact  ~normalizePath
src/graph/path-key.js                         +displayPath  ~graphKey
src/learning/weights.js                       ~sanitizeWeights  ~updateWeights  ~importWeights  ~weightsPath
src/map/config-manifest.js                    +scopeSummary  ~readText  ~readJson  ~count
src/plan/planner.js                           ~createPlan
src/wiki/generate.js                          +_rel  ~_rel  ~_flow  ~_pct
gen-context.js                                +readText  +readJson  +exists  +stripXmlComments

Read the full file on GitHub · 1,083 lines

Changes

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.

1mo ago Changed · -62 lines · -141 tokens per session 6219950bb005
1mo ago Changed · +23 lines · +267 tokens per session 901996e29293
2mo ago Changed · -285 lines · +1,098 tokens per session 18cb10caea84
2mo ago First seen · 1,407 lines · 14,533 tokens per session scan A 6d682e1399a0

Subscribe to this mod's changes

sigmap AGENTS.md is an instructions file published in the GitHub repository manojmallick/sigmap (646 stars, last pushed 4d ago), licensed MIT. It adds 15,757 tokens to every session, about $0.0630 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 2026-08-30.

Building agents LLM ai claude cursor mcp token-reduction

sigmap AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sigmap AGENTS.mdmanojmallick/sigmap	Instructions file	646	4d ago	MIT	A	15,757	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sigmap: Instructions file for Codex