agentleFS
getcargohqgetcargohq/cargo-manifest/AGENTS.md

cargo-manifest

AGENTS.md12 starsChanged 18 days agoMITView on GitHub

This repository is __APP_NAME__'s GTM engine: knowledge, infrastructure, and run history for the whole go-to-market, managed as code. It follows the Manifest framework conventions (Manifest, by Cargo). The knowledge layers ship empty, not populated. Every repeating artifact has a _template.md beside it to copy (cadence/log/, cadence/weekly/, initiatives/, outputs/, each context/<domain>/, evals/), and the four singletons that must exist by name (plan/company-plan.md, plan/strategy.md, plan/outcomes.md, cadence/carryover.md) ship as skeletons: the headings and the rules, none of the content. Nothing here is another…

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository8 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing a script to find or verify emails, find phone numbers, enrich people or companies, score leads, or sync records to a CRM, …

    line 24
  2. Very specific:

    Run it with cargo-ai orchestration action execute for one record, or execute-batch --records '<json array>' for many (after cargo-ai login).

    line 36
  3. Very specific:

    Before acting: plan/ (where we are going) then cadence/ (what matters this week) then context/ (what we know).

    line 66
  4. Distinctive:

    If you own an outcome, read its whole entry before acting: the weekly signal you report, the guardrails you must not break, the experiment …

    line 76
  5. Very specific:

    Use the cadence skill (plan the week, log the day, review the week).

    line 86
  6. Very specific:

    Write the pull request for someone who reads only its title and description (.github/PULL_REQUEST_TEMPLATE.md): the title says what it …

    line 126
  7. Very specific:

    When a task produces a real-world result (a list built, a campaign shipped, a research brief), archive it under outputs/ before finishing.

    line 164

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

APP_NAME GTM

This repository is APP_NAME's GTM engine: knowledge, infrastructure, and run history for the whole go-to-market, managed as code. It follows the Manifest framework conventions (Manifest, by Cargo).

The knowledge layers ship empty, not populated. Every repeating artifact has a _template.md beside it to copy (cadence/log/, cadence/weekly/, initiatives/, outputs/, each context/<domain>/, evals/), and the four singletons that must exist by name (plan/company-plan.md, plan/strategy.md, plan/outcomes.md, cadence/carryover.md) ship as skeletons: the headings and the rules, none of the content. Nothing here is another company's data, so there is nothing to find and delete before you start. infra/ ships empty by design too: add resources with cargo-ai cdk add cookbook/<name> or by writing them.

<!-- cargo:begin -->

Cargo

Cargo (getcargo.ai) is the go-to-market platform this project runs on, driven by the cargo-ai CLI (npx cargo-ai when it is not on your PATH). It is not Rust's cargo.

Before writing a script to find or verify emails, find phone numbers, enrich people or companies, score leads, or sync records to a CRM, check Cargo first. For emails and phones, start with the workspace's preset waterfall tools (Find email, Find phone, Verify email: several providers in one call): cargo-ai orchestration action list "find email" --kind tool, then execute-batch --action '{"kind":"tool","toolUuid":"<uuid>"}' --records '<json array>'. Single-provider actions are the fallback:

  1. cargo-ai orchestration action list <keywords> (e.g. find email). Each result carries its action object and its price in credits.
  2. cargo-ai orchestration action execute --action '<action>' --data '<json>' --dry-run checks the inputs and shows the output shape. Free, no account needed.
  3. Run it with cargo-ai orchestration action execute for one record, or execute-batch --records '<json array>' for many (after cargo-ai login).

Skills: the Cargo skill bundle lives in .agents/skills/ (linked into .claude/skills/); start with the cargo skill. Missing? Run npx skills add getcargohq/cargo-skills --all. MCP clients without a shell connect to https://mcp.getcargo.io/mcp.

<!-- cargo:end -->

Layers

LayerDirectoryWhat it is
Planplan/The destination: the one goal, the strategy, and the outcomes that must become true. Each outcome names what it becomes in infra/.
Contextcontext/What the company knows: the durable GTM brain every agent reads before acting.
Initiativesinitiatives/The big rocks: bounded efforts with an owner, a deadline, and success criteria checkable as true or false.
Cadencecadence/The operating rhythm: weekly plans, daily logs, and the carryover file that keeps dropped balls visible. Knowledge says what is true; cadence says what matters now.
Skills.agents/skills/What agents know how to do: procedures for operating this specific repo.
Infrainfra/What runs in production: the deployed engine, declared in TypeScript, reconciled by the Cargo CDK.
Scriptsscripts/What you run by hand: imperative glue for runtime-only surfaces the CDK cannot declare yet.
Evalsevals/What keeps it honest: promptfoo regression suites for agent prompts, run with npm run eval.
Outputsoutputs/What happened: the append-only archive that gives agents accumulating memory and humans an audit trail.
Scratchscratch/Yours alone: gitignored personal space with no conventions. Shared layers must never reference it.

Dependency direction is strict: infra reads context, skills read everything, outputs are written by everything and read only as memory. Nothing depends on outputs.

Read order

Before acting: plan/ (where we are going) then cadence/ (what matters this week) then context/ (what we know). Then the layer you are changing. An agent that writes copy without reading context/ will sound like a generic bot.

Working in each layer

  • plan/ holds three files and no more. Every outcome carries an owner, a metric defined well enough to calculate, a baseline, a target, and a Becomes: naming the play, agent, or tool in infra/ that makes it real. An outcome with no Becomes: is a wish.
  • If you own an outcome, read its whole entry before acting: the weekly signal you report, the guardrails you must not break, the experiment budget you may spend without asking, what you may do alone, what you must propose, and when you must escalate. Calculate the baseline before your first run. Never edit your own outcome's target, metric or guardrails: propose the change in a pull request with the evidence. New initiatives you suggest are written with status: proposed; only a person moves one to active.
  • initiatives/ is one file per bounded effort, from _template.md. Success criteria must be checkable true or false. The log is append-only.
  • cadence/ is weekly/YYYY-Www.md, log/YYYY-MM-DD.md, and carryover.md. Use the cadence skill (plan the week, log the day, review the week). An item in carryover for three weeks is a decision being avoided, not a task: escalate it.
  • context/ holds markdown with YAML frontmatter (title and description required). Domains are fixed folders (icp, persona, motion, ...); each has a _template.md. Cross-reference other files with references: in frontmatter or [[domain/slug]] wikilinks. Run npm run lint:context before committing.
  • infra/ is a self-contained Cargo CDK project. Importing a .ts file IS registration; the directory layout is convention. NEVER edit infra/cargo.state.json by hand. Secrets come from the environment via secret() and env(); never commit values.
  • .agents/skills/ is where every agent reads skills: Codex, Cursor and the skills installer natively, Claude Code through the committed symlinks in .claude/skills/. It also holds the installed Cargo skills, which are gitignored install output. A new repo skill is a real directory in .agents/skills/, one allowlist line for it and one for its symlink in .gitignore, and the symlink itself: ln -s ../../.agents/skills/<name> .claude/skills/<name>. Never copy a skill into .claude/skills/: two copies drift.
  • scripts/ is for one-off imperative operations against the workspace (memories, users, content libraries). If the CDK can declare it, it belongs in infra/ instead.
  • evals/ uses promptfoo. When you change a system prompt in infra/, update or extend the matching suite in evals/ and run npm run eval (needs an OPENAI_API_KEY). It is not wired into CI: add a workflow when the suites are worth gating on.
  • outputs/ entries are directories named outputs/YYYY-MM-DD-<slug>/, each with a README.md carrying an outcome: field (meetings, replies, pipeline attributed, or "none" with a reason). That field is what lets motions be ranked by results instead of opinions. Read recent entries for memory before starting related work. Never rewrite an existing entry. An entry can also declare a one-off run (defineBatch / defineRun) that the merge runs exactly once: it carries outcome: pending until the run finishes, and the outcome is filled in once. Use the new-execution skill.

Workflow

  1. Change context/ or infra/ on a branch. Before opening the PR, run npm run lint if you touched any prose, and npm run typecheck if you touched infra/ or scripts/. Both also run in CI.
  2. Write the pull request for someone who reads only its title and description (.github/PULL_REQUEST_TEMPLATE.md): the title says what it does, the description opens with one sentence on what happens if they approve, then the one decision only they can make and anything a person must still do by hand, each only when there is one. Then ## Why, at most three sentences, and ## Detail for everything else. Never restate what merging deploys, runs or sends: Cargo's plan says it, and a sentence written from habit can be wrong.
  3. Cargo plans the pull request and posts the diff as a comment and a check, once the repository is connected to the workspace (Settings > States). Review it the way you would review a terraform plan.
  4. Merging to main deploys. Never run cargo-ai cdk deploy locally against production. Local deploy is denied by convention and hard-blocked per agent: Claude Code (.claude/settings.json), Cursor (.cursor/rules/manifest-guardrails.mdc), and Codex (.codex/config.toml sandbox).

Rules

  • The confidence ladder. Files in proof/, signal/, and insight/ carry confidence: hypothesis | validated | proven. Outreach motions may cite only validated or proven knowledge: the linter fails the PR otherwise. A claim earns validated on its second independent occurrence. Once is an anecdote. Use the capture-feedback skill; never upgrade a claim just to unblock copy.
  • Outreach motions declare a hypothesis before any copy exists: segment, angle, trigger, expected_reply_rate. Enrichment, scoring, routing, and signal plays are not campaigns and are exempt: they declare intent through the outcome they serve in plan/outcomes.md. Every motion sets kind:.
  • Absolute dates everywhere. 2026-07-14, never "next quarter".
  • Append-only history. Outputs and logs are corrected with a dated addendum, never rewritten. A major context rewrite archives the prior version instead of overwriting it.
  • New motions: use the new-motion skill. It creates context/motion/<name>.md, the implementation in infra/, and evals/<name>/ together so the three layers never drift apart.
  • Copy style: no em dashes anywhere. Use colons, parentheses, commas, or split the sentence.
  • When a task produces a real-world result (a list built, a campaign shipped, a research brief), archive it under outputs/ before finishing.
  • Something to run once (enroll a list, backfill a field) is an execution in outputs/, not a script and not a local run: use the new-execution skill, so it is previewed on the PR and runs exactly once on merge.
  • Personal vs shared: experiments and personal mess go in scratch/ (gitignored), personal skills in ~/.claude/skills/, personal instructions in CLAUDE.local.md. Work enters the shared layers only through a PR, once it has proven itself. If asked to save something and it is not clearly team-ready, default to scratch/.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.