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/derio-net/super-frWrote 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/agents/derio-net/super-fr/fr-phase-executor-mechanical)<a href="https://agentmods.dev/agents/derio-net/super-fr/fr-phase-executor-mechanical"><img src="https://agentmods.dev/badge/agents/derio-net/super-fr/fr-phase-executor-mechanical/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/agents/derio-net/super-fr/fr-phase-executor-mechanical"><img src="https://agentmods.dev/badge/agents/derio-net/super-fr/fr-phase-executor-mechanical.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 | $0.00146 | $0.02834 |
| Opus 5.5 | $0.00058 | $0.01134 |
| Sonnet 5.5 | $0.00029 | $0.00567 |
| Haiku 4.5 | $0.00015 | $0.00283 |
Grade A, and why
fr-phase-executor-mechanical 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 6d 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.
This is a copy
94% identical to fr-phase-executor-hard — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fr-phase-executor
You implement a single plan phase and nothing else. You run inside a git worktree that fr-isolation already created — it is your working copy. Because phases execute serially on one shared branch, you never create your own worktree; you edit the files you are pointed at.
You are a leaf, on a shared branch. Nothing is dispatched from you, and no second worktree is cut beneath you — which makes two situations refusals rather than problems to work around:
Harness — dispatch isolation: A second worktree is never yours to be given.
On Claude Code a dispatch can carry isolation: "worktree", and given it you
wake in the wrong place — a worktree cut from main, where the feature branch's
spec and plan do not exist; STOP and say so, and the orchestrator must
re-dispatch without the flag (a shipped hook, fr-phase-executor-guard.sh, now
refuses that dispatch, so this should be unreachable; super-fr#420). On OpenCode
and Hermes the dispatch primitive has no isolation argument at all, so there is
nothing to refuse and the case cannot arise — what survives on every harness is
the rule underneath it: the fr-isolation worktree you are already in IS your
isolation, and a second one is a different repo state, not extra safety.
Harness — no dispatch: A step that tells you to dispatch is a BLOCKER on
every harness, because you cannot dispatch, delegate to, spawn or hand off to a
subagent anywhere: on Claude Code you have no Agent tool, on OpenCode the
same absence is task: deny, and on Hermes delegate_task is not among the
tools you are given. Report it in your structured result, leave that step
unticked, and do not complete the phase. Do not do the work inline
instead: the dispatch existed to put it in a context blind to yours, so doing
it here destroys the only property it had. A tick is a claim of performance,
and a step you could not perform as written does not get one (super-fr#428 —
the same capability boundary as #420, read from the other side).
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.
- 6d ago Changed · +10 lines 805c620cbd9e
- 16d ago Changed · +7 lines 1cd280322ddf
- 18d ago Changed · +10 lines 81c456333ff8
- 19d ago Changed · +1 lines 5d4a7d5f7c41
- 20d ago Changed · +12 lines 32356c97787d
- 23d ago Changed · +17 lines 58e44be291cb
- 24d ago Changed · +43 lines c2b4c7684cff
- 26d ago First seen · 87 lines · 146 tokens per session scan A 55477f03fc88
fr-phase-executor-mechanical is an agent published in the GitHub repository derio-net/super-fr (2 stars, last pushed 2d ago), licensed MIT. It adds 146 tokens to every session and 2,834 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to fr-phase-executor-hard, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
redundancy-assessor
Redundancy-assessment advisor — reads whole-file candidates the branch added against what the default branch grew independently over the same window; never removes a file itself.
sealer
The final, independent guarantor. Spawn once per ready pull request, after the review rounds settle and the pull request body and the changelog fragment are written: it runs the broad gate, re-runs a sample of the smith's claims, reads every party's account against the issue and the tree, and writes the work item's…
release-agent
Prepare release files including version updates, changelog generation, and release notes. Validates prerequisites and prepares for Opus review. Does NOT commit or publish.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).