aigon-feature-spec-revise

aigon-feature-spec-revise is a skill for Claude Code, Codex from jayvee/aigon. It costs 22 tokens per session (604 once invoked), scanned A, original, Apache-2.0.

A workflow for revising a feature specification after other developers have reviewed it.

In plain words
What is it for?
Use it to find review commits for a feature specification, update the document where needed, and create an acknowledgement commit.
Why use it?
It gathers pending review comments, decides which changes to accept, and records the author’s decisions so the review does not remain unresolved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

Good fit Use it to find review commits for a feature specification, update the document where needed, and create an acknowledgement commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jayvee/aigon/aigon-feature-spec-revise
Install

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.

Any agent
npx skills add jayvee/aigon --skill aigon-feature-spec-revise
Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aigon-feature-spec-revise

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayvee/aigon/aigon-feature-spec-revise/github.svg)](https://agentmods.dev/skills/jayvee/aigon/aigon-feature-spec-revise)
Your own site
<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-feature-spec-revise"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-feature-spec-revise/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.

agentmods 80×15 button for aigon-feature-spec-revise

Your own site · 80×15
<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-feature-spec-revise"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-feature-spec-revise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00604
Opus 5 $0.00011 $0.00302
Sonnet 5 $0.00004 $0.00121
Haiku 4.5 $0.00002 $0.00060

Measured 9d ago against content hash e88372ca4953, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aigon-feature-spec-revise 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 9d 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.

.agents/skills/aigon-feature-spec-revise/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-feature-spec-revise

You are the author-side agent. Review all pending spec-review: commits on the feature spec, decide what to keep, and land one acknowledgement commit.

The continuity strategy is selected by Aigon before launch. Do not choose a provider or resume strategy yourself. When resumed, reconcile remembered paths against the current checkout and emit the requested continuation ready/fallback checkpoint before editing.

Resolve the spec

SPEC_PATH=$(aigon feature-spec $1 2>/dev/null || true)
if [ -z "$SPEC_PATH" ]; then
  SPEC_PATH=$(find docs/specs/features -maxdepth 2 \( -name "feature-$1-*.md" -o -name "feature-$1.md" \) | head -1)
fi
test -n "$SPEC_PATH" && echo "$SPEC_PATH"

If SPEC_PATH is empty, stop and report that the feature spec could not be resolved.

Find pending review commits

Find the latest acknowledgement, if any:

LAST_ACK=$(git log --follow --format=%H -n 1 --grep='^spec-review-check:' --grep='^spec-revise:' -- "$SPEC_PATH")
echo "last_ack=${LAST_ACK:-none}"

Then inspect pending reviews newer than that acknowledgement:

git log --follow --format='%H %s' -- "$SPEC_PATH"

Pending reviews are commits whose subject starts with spec-review: and are newer than LAST_ACK if LAST_ACK exists.

For every pending review commit:

git show <sha> -- "$SPEC_PATH"
git show -s --format=%B <sha>

Decide in one pass

Process all pending reviewers together. Your options are:

  • Accept: keep the reviewed spec as-is.
  • Revert: revert one or more review commits.
  • Modify: keep the reviewer intent but make follow-up edits before acknowledging.

If you need changes, make them before the acknowledgement commit.

Acknowledge with one commit

After the spec is in its final state, commit exactly once with:

git add "$SPEC_PATH"
git commit --allow-empty -m "spec-revise: feature $1 — <decision summary>" -m "reviewed: <comma-separated reviewer ids>

Decision:
- <accept|revert|modify summary>

Notes:
- <important rationale>"
aigon feature-spec-revise-record $1

Read the full file on GitHub · 86 lines

Changes

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.

  1. 9d ago First seen · 86 lines · 22 tokens per session scan A e88372ca4953

Subscribe to this mod's changes

aigon-feature-spec-revise is a skill published in the GitHub repository jayvee/aigon (25 stars, last pushed 8d ago), licensed Apache-2.0. It adds 22 tokens to every session and 604 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

claude-code-expert

Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.

aAAaqwq/AGI-Super-Team · 59 tokens

dos-goal-fleet

Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.

anthony-chaudhary/dos-kernel · 51 tokens

dos-goal-gate

Ground a keep-working goal in evidence the worker did not author by wiring dos hook stop to refuse false done claims. Use for one self-stopping agent or loop worker; use dos-witness-claim for fold barriers.

anthony-chaudhary/dos-kernel · 54 tokens

dos-dispatch-loop

Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.

anthony-chaudhary/dos-kernel · 49 tokens

dos-supervise-loop

Keep a target count of dispatch loops alive across the workspace lane roster: spawn missing loops, scavenge stalled leases, and surface spinning workers. Use when supervising a DOS dispatch-loop fleet.

anthony-chaudhary/dos-kernel · 43 tokens

dos-witness-claim

Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.

anthony-chaudhary/dos-kernel · 47 tokens