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.
git clone --depth 1 https://github.com/AnEntrypoint/freddieWrote 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/commands/anentrypoint/freddie/agents)<a href="https://agentmods.dev/commands/anentrypoint/freddie/agents"><img src="https://agentmods.dev/badge/commands/anentrypoint/freddie/agents/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/commands/anentrypoint/freddie/agents"><img src="https://agentmods.dev/badge/commands/anentrypoint/freddie/agents.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 | $0.00000 | $0.00313 |
| Opus 5.5 | $0.00000 | $0.00125 |
| Sonnet 5.5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
AGENTS 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 16d 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
AGENTS.md — commands
Rationale
src/index.jsrun path: cancellation is checked after admission and BEFORE the handler runs. Admission may await slow storage, and a handler entered after the caller cancelled would mutate state the retrying caller then duplicates (the committed image objects stay unreferenced, left to deferred GC).src/index.jslog-only append:session.append.bind(session)is called with two arguments on purpose; TypeScript does not reduceSession.append's conditional rest parameter through a generic type parameter.src/index.jscommands/changenotification: CordisemitusesArray.map, so one synchronous throw would starve later listeners and returned promises are dropped. Notifications are non-vetoing; each callback is contained and its rejection logged.src/invariant.js: the run-id set is install-scoped so a dispose/re-register cycle re-sweeps from a clean slate.command/runis appended before the handler andcommand/doneafter settlement; admission misses log nothing; images to a command lackinginput.images, an absent attachment store, or an exceeded limit settle as error results before the handler runs. Lifecycle events are direct log-only appends with no turn and no forced flush.- Command ids are monotonic and prefixed with an instance token so a resumed log never repeats one.
typert.host.jsandtypert.remote-client.jsare hand-owned Typert manifests (Remote RPC schema and reflection metadata).
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.
- 16d ago First seen · 12 lines · 0 tokens per session scan A 4b5b275ac59e
AGENTS is a command published in the GitHub repository AnEntrypoint/freddie (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 313 tokens. 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 2026-09-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.