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 skills add skyfox675/agents-skills --skill technical-recongit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/skills/skyfox675/agents-skills/technical-recon)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/technical-recon"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/technical-recon/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/skills/skyfox675/agents-skills/technical-recon"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/technical-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00211 | $0.03588 |
| Opus 5 | $0.00105 | $0.01794 |
| Sonnet 5 | $0.00042 | $0.00718 |
| Haiku 4.5 | $0.00021 | $0.00359 |
Grade A, and why
technical-recon 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 8d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Recon: scope, size, and de-risk a groomed issue before dispatch
An issue can be fully groomed and accepted by stakeholders — clear symptom, desired behaviour, acceptance criteria — and still be unsafe to dispatch, because nobody on the dev team has confirmed how it would be built, how big it is, or what it might break. Technical recon closes that gap: a read-only sub-agent traces the ask into the actual codebase and returns an implementation approach, a level-of-effort estimate, the risks, and a dispatch recommendation. The issue moves from "stakeholders want this" to "the dev team knows what this costs and how to build it."
This is not the intake-triage recon in the issue-filing skill (gh-issue-filing / jira-issue-filing). That one runs a cheap model to classify stub issues into ready-to-dispatch / needs-spec-input / blocked by a five-rule decision tree, with a capped blast radius. Technical recon is the opposite end: the issue is already groomed, and the question is the engineering answer — design, cost, risk — which needs a capable model reading real code, not a cheap classifier. The two compose: intake-triage decides an issue is specified; technical recon decides it is buildable and sized.
Compose with the siblings: dispatch the recon agents with the dispatching-subagents skill; read the issue and post findings with the issue-filing skill's anatomy conventions; set the resulting labels/fields with the control-field skill (gh-issue-labels for GitHub, jira-issue-fields for Jira); and when recon clears an issue, the orchestrating-slots loop dispatches the implementation per the issue-locking skill (gh-issue-locking / jira-issue-locking). Recon itself never claims, never writes code, never opens a PR.
Project bindings
Define these in the adopting project's CLAUDE.md; the body refers to them by placeholder.
| Binding | Meaning | Example |
|---|---|---|
<loe-scale> |
The LoE vocabulary the team estimates in | T-shirt XS|S|M|L|XL (below) |
<recon-model> |
Model tier for recon — a capable one, never the cheap tier | sonnet (escalate to opus for deep/cross-cutting asks) |
<vetted-state> |
The label/status meaning "dev-vetted, ready to dispatch" | ready-to-dispatch |
<needs-input-state> |
"a technical decision must be made before build" | needs-spec-input |
<blocked-state> |
"a dependency must land first" | blocked |
<loe-field> |
Where the size is recorded | a loe:<size> label, or the Jira Story-points / a custom field |
<shared-surfaces> |
Contention-prone files that mark the plumbing lane (see the issue-filing skill) | DB schema, API schema, shared types, design tokens, root manifest/lockfile |
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.
- 8d ago First seen · 140 lines · 211 tokens per session scan A 85ddc2183de8
technical-recon is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 211 tokens to every session and 3,588 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.