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/evoelsewhere/evoflux/easd-plannpx skills add evoelsewhere/evoflux --skill easd-plangit clone --depth 1 https://github.com/evoelsewhere/evofluxWhat 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 | $0.00039 | $0.00928 |
| Opus 5 | $0.00019 | $0.00464 |
| Sonnet 5 | $0.00008 | $0.00186 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
easd-plan 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan an accepted EASD specification
Repository contract
Read .evoflux/easd/config.json and its rules_file before phase work. Treat
the injected EASD context as the authoritative current Run; when the owning
runtime is accessible, corroborate it under runtime_directory. An isolated
worktree intentionally has no checkout-local runtime copy. Resolve the accepted
revision through the Run's common specs/ catalogue index and confirm its hash
matches the Run snapshot. Read affected current-state knowledge without
relocating existing project docs. Repository documents are the shared source of
truth. Stop on a missing tracked contract, stale hash, generation conflict, or
unavailable injected runtime; never reconstruct authority from chat memory or a
stale database-only projection. If the accepted Spec selected direct, stop: Plan
is intentionally skipped and this Skill has no authority.
Build the execution map from the exact accepted specification hash. Planning does not authorize implementation and must not weaken the accepted contract.
State gate
Re-read the current run and accepted revision before planning. Stop if there is
no accepted hash, if the hash differs from the one supplied to this turn, or if
the run is terminal. accepted waits for the user's Run plan action;
planning permits one typed plan submission; plan_review is human review and
cannot be overwritten by the agent; planned belongs to implementation. If the
accepted revision changes, discard the stale plan and compile from the new hash.
Compile the work
- Confirm the run ID, accepted spec hash, status, risk tier, ACs, impact targets, constraints, and evidence policies from injected EASD context.
- Map every required AC to an implementation owner and concrete files/modules, dependencies, and expected evidence. Add explicit verification missions that collectively own every accepted Proof command; a command without a Verify owner is a plan gap, not an implementation detail.
- Put shared contracts before dependent layers. Record the exact interface each slice consumes and produces. Split parallel missions by disjoint ownership; name one integration owner wherever overlap is necessary.
- Add a separate review mission for every run. Apply independence in proportion
to risk: cross-layer and critical review must be owned by someone who did not
author the affected change, and its task should explicitly request EASD
independent review so the repository's
easd-reviewSkill can be selected. - Include negative paths, migration/compatibility, security, observability, documentation, and rollback work only where the accepted specification or affected boundary requires them.
- Order slices so each ends in a behavior that can be tested and reviewed independently. For observable changes and regressions, plan the failing test or other baseline observation before the implementation that makes it pass.
- Run an implementability check: a developer or specialist must be able to execute every slice without inventing product behavior, interface ownership, setup, or verification. Return real gaps to specification/design instead of hiding them in task prose.
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.
- 2d ago First seen · 85 lines · 39 tokens per session scan A 8c5ee1d77089
easd-plan is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 39 tokens to every session and 928 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
E2E Testing Nori Skillsets Subcommands
Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation.
changelog-generator
Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…
token-saver-config
Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.
issue-review
Triage a copperhead GitHub issue, attempt reproduction, and check it against the spec. Use when the user asks to review an issue, e.g. /issue-review 42 or /issue-review .
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…