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 skills/cofin/flow/flow-executionnpx skills add cofin/flow --skill flow-executiongit clone --depth 1 https://github.com/cofin/flowWhat 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 | $0.00050 | $0.00739 |
| Opus 5 | $0.00025 | $0.00369 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
flow-execution 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Execution
Trigger
Use for implement only, after a validated plan contains ready task worksheets.
contract: worksheet-execution-v1
invariants:
- worksheet-first
- fail-closed-no-production-mutation
- fresh-validated-plan-resume
transitions:
- preflight-claim
- mismatch-discover-block
- nonblocking-discover-release
- revised-plan-resume
authority: skills/flow/references/implement.md
Workflow
- Preflight: Inspect
.agents/bundles/specs/<flow_id>/tasks/<short_id>.md, verify dependencies areclosed, and apply a journaledclaimthroughflow-statewith the expected plan identity and spec state revision. - Initial Evidence: Collect the declared strategy's required initial proof; only behavior and regression strategies require red.
- Minimal Implementation: Make the smallest task-owned change while keeping focused evidence green.
- Quality Gates: Run repository linters and typecheckers while tests remain green.
- Atomic Commit & Close: Stage exact files, commit, apply a journaled
closethroughflow-staterecordingcommit: <sha>, and reconcile thespec.mdchecklist via/flow:sync.
Guardrails
- Execute exactly one task per subagent dispatch.
- Never mark a task
closedwithout running the test command and observing exit code 0. - Stage only task-owned files; never perform opportunistic unrelated edits.
- Work on the active branch. Never create or mutate Git tags.
Strategy Evidence
| Strategy | Initial evidence | Final evidence |
|---|---|---|
behavior_tdd |
Focused behavior test fails because behavior is absent. | Focused test and relevant aggregate verification pass. |
regression_tdd |
Focused reproduction fails with the reported symptom. | Regression and relevant aggregate verification pass. |
characterization |
Focused behavior baseline passes before cleanup. | Same behavior passes unchanged; compare affected coverage when needed. |
static_validation |
Native parser, lint, type, build, or generator baseline runs. | Isolated representative violation produces the expected diagnostic; restored focused and aggregate gates pass. |
documentation_validation |
Documentation-native baseline runs. | Documentation checks and promised examples pass. |
integration_acceptance |
Focused integration baseline passes. | End-to-end scenario passes; injected negative states prove refusal paths. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 72 lines · 50 tokens per session scan A 1eb1065e2756
flow-execution is a skill published in the GitHub repository cofin/flow (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 739 once invoked, about $0.0003 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 skills, from other repositories
write-documentation
Use when writing or substantially rewriting human-facing prose: documentation, README, guides, blog posts, emails, Slack messages, PR descriptions, release notes, or any text a human will read. Not for code comments, commit messages, or agent-to-agent communication.
document-release
Use when implementation on a branch is complete and it is about to be merged or PR'd — or when finishing-a-development-branch reaches its docs-audit gate — and after code changes are committed, to ensure all project documentation accurately reflects shipped code. Covers README, ARCHITECTURE, CONTRIBUTING, CHANGELOG…
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.